Article(id=1329381583255090021, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329381463562236291, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202220935, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1668096000000, receivedDateStr=2022-11-11, revisedDate=1684080000000, revisedDateStr=2023-05-15, acceptedDate=null, acceptedDateStr=null, onlineDate=1794878868162, onlineDateStr=2026-11-17, pubDate=1704124800000, pubDateStr=2024-01-02, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794878868162, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794878868162, creator=13701087609, updateTime=1794878868162, updator=13701087609, issue=Issue{id=1329381463562236291, tenantId=1146029695717560320, journalId=1324759914146529478, year='2024', volume='61', issue='1', pageStart='1', pageEnd='270', issueExtLink='null', onlineDate='null', pubDate='1704124800000', pubDateStr='2024-01-02', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794878839626, creator='13701087609', updateTime=1794899256120, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1329467096993477032, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329381463562236291, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1329467096997671337, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329381463562236291, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=120, endPage=144, ext={EN=ArticleExt(id=1329381583452222310, articleId=1329381583255090021, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Survey of Universal Domain Adaptation, columnId=1325489891789910943, journalTitle=Journal of Computer Research and Development, columnName=Artificial Intelligence, runingTitle=null, highlight=null, articleAbstract=
Domain adaptation relaxes the assumption that test data follows the same distribution as training data in traditional machine learning, and transfers knowledge from label-rich source domain to label-scarce target domain when domain bias exists. However, most domain adaptation methods make assumptions about the relative relationship between the label space of source domain and target domain which limits the application of these methods in reality. Therefore, universal domain adaptation is proposed to label target data without prior information of label spaces of source domain and target domain. Generally, a universal domain adaptation model needs to solve several problems. Firstly, it is desired to judge whether a target sample belongs to classes in source domain. Then it ought to transfer knowledge of common classes shared by source domain and target domain to label target samples, as well as dealing with the domain bias and potential category shift. Due to its practicability, universal domain adaptation has gained more and more attention now. Many branches of universal domain adaptation have been proposed, and researchers are trying to apply it onto datasets different from images. In this review, we conduct an exhaustive survey of universal domain adaptation methods till now from the point of problem setting and strategies. Then we compare typical methods and analyze the difficulties in the universal domain adaptation. After that, we introduce current applications of universal domain adaptation. Meanwhile, we analyze relevant research areas briefly. Lastly, we discuss the problems of universal domain adaptation that can be studied further.
, authors=Qiuyan He
1, Minghua Deng
1, 2, 3, *, authorsList=Qiuyan He, Minghua Deng, authorCompany=null, correspAuthors=Minghua Deng, authorNote=
born in 1997. PhD candidate. Her main research interests include bioinformatics and machine learning
born in 1969. PhD, professor, PhD supervisor. His main research interests include bioinformatics and computational biology
, correspAuthorsNote=null, copyrightStatement=Copyright © 2024 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1329381586262406019, articleId=1329381583255090021, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=通用域适应综述, columnId=1325489892104483745, journalTitle=计算机研究与发展, columnName=人工智能, runingTitle=null, highlight=null, articleAbstract=
域适应问题放宽了传统机器学习问题关于训练样本和测试样本同分布的假设,在域间差异存在的情况下从富有标签的源域迁移知识到缺少标签的目标域. 但现有域适应方法大多依赖于对源域和目标域标签集合的相对关系的假设,不贴合实际应用场景,因此,通用域适应问题考虑如何在缺少源域和目标域的标签集合先验信息的情况下,实现对目标域的标记. 在此过程中,通用域适应方法需要判定目标域样本是否属于源域类别,克服域间差异和潜在的类别差异,在源域和目标域共有类上完成标签的迁移. 首先从问题设置与方法策略2方面,对通用域适应方法进行梳理;然后通过实验对比了典型方法,进而分析了通用域适应问题的研究难点;随后整理了现有方法的应用情况,对与之有关的实际应用问题进行了分析;最后探讨了通用域适应问题未来研究方向.
, authors=何秋妍
1, 邓明华
1, 2, 3, *, authorsList=何秋妍, 邓明华, authorCompany=null, correspAuthors=邓明华, authorNote=
 |
1997年生. 博士研究生. 主要研究方向为生物信息学、机器学习 |
 |
1969年生. 博士,教授,博士生导师. 主要研究方向为生物信息学、计算生物学 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2024 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=0CtCQ1xik1gulGkz3Uvpeg==, magXml=KNLqReBfR81y66lVx8iOVw==, pdfUrl=null, pdf=SnIM/bcYssx0C1snH+Aw3w==, pdfFileSize=3117923, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=qsuU8PzHzCqbVv8WZEr9CQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=92evcmhFjkv38Y79ciBgLw==, mapNumber=null, fund=null)}, authors=[Author(id=1329381586753139598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=heqy@pku.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329381586820248464, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, authorId=1329381586753139598, language=EN, stringName=Qiuyan He, firstName=Qiuyan, middleName=null, lastName=He, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Mathematical Sciences, Peking University, Beijing 100871, bio={"content":"
born in 1997. PhD candidate. Her main research interests include bioinformatics and machine learning
"}, bioImg=null, bioContent=
born in 1997. PhD candidate. Her main research interests include bioinformatics and machine learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329381586883163025, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, authorId=1329381586753139598, language=CN, stringName=何秋妍, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1北京大学数学科学学院 北京 100871, bio={"img":"JpVB+ot7n7GaF6K3Z6siHQ==","content":"
1997年生. 博士研究生. 主要研究方向为生物信息学、机器学习
"}, bioImg=JpVB+ot7n7GaF6K3Z6siHQ==, bioContent=
1997年生. 博士研究生. 主要研究方向为生物信息学、机器学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329381586505675652, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, xref=1, ext=[AuthorCompanyExt(id=1329381586514064261, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586505675652, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Mathematical Sciences, Peking University, Beijing 100871), AuthorCompanyExt(id=1329381586522452870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586505675652, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1北京大学数学科学学院 北京 100871)])]), Author(id=1329381586954466195, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=dengmh@math.pku.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329381587046740887, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, authorId=1329381586954466195, language=EN, stringName=Minghua Deng, firstName=Minghua, middleName=null, lastName=Deng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, 3, *, address=
1School of Mathematical Sciences, Peking University, Beijing 100871
2Center for Statistical Science, Peking University, Beijing 100871
3Center for Quantitative Biology, Peking University, Beijing 100871, bio={"content":"
born in 1969. PhD, professor, PhD supervisor. His main research interests include bioinformatics and computational biology
"}, bioImg=null, bioContent=
born in 1969. PhD, professor, PhD supervisor. His main research interests include bioinformatics and computational biology
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329381587113849752, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, authorId=1329381586954466195, language=CN, stringName=邓明华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, 3, *, address=
1北京大学数学科学学院 北京 100871
2北京大学统计科学中心 北京 100871
3北京大学定量生物学中心 北京 100871, bio={"img":"R8eeLIsQHxtCEnKFQmWang==","content":"
1969年生. 博士,教授,博士生导师. 主要研究方向为生物信息学、计算生物学
"}, bioImg=R8eeLIsQHxtCEnKFQmWang==, bioContent=
1969年生. 博士,教授,博士生导师. 主要研究方向为生物信息学、计算生物学
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329381586505675652, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, xref=1, ext=[AuthorCompanyExt(id=1329381586514064261, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586505675652, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Mathematical Sciences, Peking University, Beijing 100871), AuthorCompanyExt(id=1329381586522452870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586505675652, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1北京大学数学科学学院 北京 100871)]), AuthorCompany(id=1329381586581173127, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, xref=2, ext=[AuthorCompanyExt(id=1329381586589561736, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586581173127, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Center for Statistical Science, Peking University, Beijing 100871), AuthorCompanyExt(id=1329381586597950345, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586581173127, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2北京大学统计科学中心 北京 100871)]), AuthorCompany(id=1329381586669253514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, xref=3, ext=[AuthorCompanyExt(id=1329381586673447819, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586669253514, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3Center for Quantitative Biology, Peking University, Beijing 100871), AuthorCompanyExt(id=1329381586681836428, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586669253514, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3北京大学定量生物学中心 北京 100871)])])], keywords=[Keyword(id=1329381587231290265, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, orderNo=1, keyword=universal domain adaptation), Keyword(id=1329381587302593434, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, orderNo=2, keyword=transfer learning), Keyword(id=1329381587386479515, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, orderNo=3, keyword=adversarial learning), Keyword(id=1329381587436811164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, orderNo=4, keyword=contrastive learning), Keyword(id=1329381587520697245, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, orderNo=5, keyword=self-training), Keyword(id=1329381587608777630, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, orderNo=1, keyword=通用域适应), Keyword(id=1329381587663303583, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, orderNo=2, keyword=迁移学习), Keyword(id=1329381587755578272, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, orderNo=3, keyword=对抗学习), Keyword(id=1329381587818492833, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, orderNo=4, keyword=对比学习), Keyword(id=1329381587889796002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, orderNo=5, keyword=自训练)], refs=[Reference(id=1329381592654525406, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Pan Jialin Sinno, Yang Qiang. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345−1359, articleTitle=null, refAbstract=null), Reference(id=1329381592704857055, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=范苍宁,刘鹏,肖婷,等. 深度域适应综述:一般情况与复杂情况[J]. 自动化学报,2021,47(3):515−548, articleTitle=null, refAbstract=null), Reference(id=1329381592767771616, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Fan Cangning, Liu Peng, Xiao Ting, et al. A review of deep domain adaptation: General situation and complex situation[J]. Acta Automatica Sinica, 2021, 47(3): 515−548 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329381592822297569, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Zhangjie, Long Mingsheng, Wang Jianmin, et al. Partial transfer learning with selective adversarial networks [C]// Proc of the 31st IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 2724−2732, articleTitle=null, refAbstract=null), Reference(id=1329381592885212130, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Jing, Ding Zewei, Li Wanqing, et al. Importance weighted adversarial nets for partial domain adaptation [C]// Proc of the 31st IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 8156−8164, articleTitle=null, refAbstract=null), Reference(id=1329381592943932387, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Busto P P, Gall J. Open set domain adaptation [C]// Proc of the 15th IEEE Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2017: 754−763, articleTitle=null, refAbstract=null), Reference(id=1329381593006846948, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Saito K, Yamamoto S, Ushiku Y, et al. Open set domain adaptation by backpropagation [C]// Proc of the 15th European Conf on Computer Vision (ECCV). Berlin: Springer, 2018: 156−171, articleTitle=null, refAbstract=null), Reference(id=1329381593061372901, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=You Kaichao, Long Mingsheng, Cao Zhangjie, et al. Universal domain adaptation [C]// Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2019: 2715−2724, articleTitle=null, refAbstract=null), Reference(id=1329381593183007718, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Farahani A, Voghoei S, Rasheed K, et al. A brief review of domain adaptation [C]// Proc of the 16th Int Conf on Data Science (ICDATA) and the 19th Int Conf on Information & Knowledge Engineering (IKE). Berlin: Springer, 2021: 877−894, articleTitle=null, refAbstract=null), Reference(id=1329381593258505191, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Kundu J N, Venkat N, Rahul M V, et al. Universal source-free domain adaptation [C]// Proc of the 33rd IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2020: 4543−4552, articleTitle=null, refAbstract=null), Reference(id=1329381593342391272, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Liang Jian, Hu Dapeng, Feng Jiashi, et al. UMAD: Universal model adaptation under domain and category shift [J]. arXiv preprint, arXiv: 2112.08553, 2021, articleTitle=null, refAbstract=null), Reference(id=1329381593413694441, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Deng Bin, Zhang Yabin, Tang Hui, et al. On universal black-box domain adaptation [J]. arXiv preprint, arXiv: 2104.04665, 2021, articleTitle=null, refAbstract=null), Reference(id=1329381593484997610, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Yin Yueming, Yang Zhen, Hu Haifeng, et al. Universal multi-source domain adaptation for image classification[J]. Pattern Recognition, 2022, 121(1/2): 108238, articleTitle=null, refAbstract=null), Reference(id=1329381593560495083, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Qing, Hashimoto A, Ushiku Y. Divergence optimization for noisy universal domain adaptation [C]// Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2021: 2515−2524, articleTitle=null, refAbstract=null), Reference(id=1329381593623409644, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Xinhong, Gao Junyu, Xu Changsheng. Active universal domain adaptation [C]// Proc of the 18th IEEE/CVF Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2021: 8948−8957, articleTitle=null, refAbstract=null), Reference(id=1329381593694712813, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Chidlovskii B, Sadek A, Wolf C. Universal domain adaptation in ordinal regression [J]. arXiv preprint, arXiv: 2106.11576, 2021, articleTitle=null, refAbstract=null), Reference(id=1329381593766015982, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Fu Bo, Cao Zhangjie, Long Mingsheng, et al. Learning to detect open classes for universal domain adaptation [C]// Proc of the 16th European Conf on Computer Vision (ECCV). Berlin: Springer, 2020: 567−583, articleTitle=null, refAbstract=null), Reference(id=1329381593833124847, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Yin Yueming, Yang Zhen, Wu Xiaofu, et al. Pseudo-margin-based universal domain adaptation[J]. Knowledge-Based Systems, 2021, 229(1/2): 107315, articleTitle=null, refAbstract=null), Reference(id=1329381593900233712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Ziyun, Song Jie, Zhang Tengfei, et al. Dual contrastive universal adaptation network [C/OL]// Proc of the 22nd IEEE Int Conf on Multimedia and Expo (ICME). Piscataway, NJ: IEEE, 2021[2022-09-09].https://ieeexplore.ieee.org/document/9428238, articleTitle=null, refAbstract=null), Reference(id=1329381593971536881, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Wei, Li Xiang, Ma Hui, et al. Universal domain adaptation in fault diagnostics with hybrid weighted deep adversarial learning[J]. IEEE Transactions on Industrial Informatics, 2021, 17(12): 7957−7967, articleTitle=null, refAbstract=null), Reference(id=1329381594051228658, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Lifshitz O, Wolf L. Sample selection for universal domain adaptation [C]// Proc of the 35th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2021: 8592−8600, articleTitle=null, refAbstract=null), Reference(id=1329381594114143219, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Yuan, Chen Peipeng, Gao Yue, et al. Hierarchical feature disentangling network for universal domain adaptation[J]. Pattern Recognition, 2022, 127(1): 108616, articleTitle=null, refAbstract=null), Reference(id=1329381594185446388, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Liang, Lou Yihang, He Jianzhong, et al. Geometric anchor correspondence mining with uncertainty modeling for universal domain adaptation [C]// Proc of the 35th IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2022: 16134−16143, articleTitle=null, refAbstract=null), Reference(id=1329381594248360949, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Ren Yu, Cong Yang, Dong Jiahua, et al. Uni3DA: Universal 3D domain adaptation for object recognition[J]. IEEE Transactions on Circuits and Systems for Video Technolny, 2023, 33(1): 379−392, articleTitle=null, refAbstract=null), Reference(id=1329381594319664118, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Saito K, Kim D, Sclaroff S, et al. Universal domain adaptation through self-supervision [C]// Proc of the 33rd Int Conf on Neural Information Processing Systems. New York: Curran Associates, Inc, 2020: 16282−16292, articleTitle=null, refAbstract=null), Reference(id=1329381594382578679, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Cho J. Synthetic source universal domain adaptation through contrastive learning [J]. Sensors, 2021, 21(22): 7539, articleTitle=null, refAbstract=null), Reference(id=1329381594470659064, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Ronghang, Li Sheng. Self-supervised universal domain adaptation with adaptive memory separation [C]// Proc of the 21st IEEE Int Conf on Data Mining (ICDM). Piscataway, NJ: IEEE, 2021: 1547−1552, articleTitle=null, refAbstract=null), Reference(id=1329381594529379321, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Guangrui, Kang Guoliang, Zhu Yi, et al. Domain consensus clustering for universal domain adaptation [C]// Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2021: 9752−9761, articleTitle=null, refAbstract=null), Reference(id=1329381594600682490, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Liang, Du Qianjin, Lou Yihang, et al. Mutual nearest neighbor contrast and hybrid prototype self-training for universal domain adaptation [C]// Proc of the 36th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2022: 6248−6257, articleTitle=null, refAbstract=null), Reference(id=1329381594659402747, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Saito K, Saenko K. OVANet: One-vs-all network for universal domain adaptation [C]// Proc of the 18th IEEE/CVF Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2021: 8980−8989, articleTitle=null, refAbstract=null), Reference(id=1329381594730705916, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Liang, Lou Yihang, He Jianzhong, et al. Evidential neighborhood contrastive learning for universal domain adaptation [C]// Proc of the 36th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2022: 6258−6267, articleTitle=null, refAbstract=null), Reference(id=1329381594802009085, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Ganin Y, Lempitsky V. Unsupervised domain adaptation by backpropagation [C]// Proc of the 32nd Int Conf on Machine Learning. New York: PMLR, 2015: 1180−1189, articleTitle=null, refAbstract=null), Reference(id=1329381594860729342, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Kang Guoliang, Jiang Lu, Yang Yi, et al. Contrastive adaptation network for unsupervised domain adaptation [C]// Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2019: 4888−4897, articleTitle=null, refAbstract=null), Reference(id=1329381594923643903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Niu Zhenxing, Zhou Mo, Wang Le, et al. Ordinal regression with multiple output CNN for age estimation [C]// Proc of the 29th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2016: 4920−4928, articleTitle=null, refAbstract=null), Reference(id=1329381594982364160, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Wenzhi, Mirjalili V, Raschka S. Rank consistent ordinal regression for neural networks with application to age estimation[J]. Pattern Recognition Letters, 2020, 140: 325−331, articleTitle=null, refAbstract=null), Reference(id=1329381595045277696, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Verma V, Lamb A, Beckham C, et al. Manifold mixup: Better representations by interpolating hidden states [C]// Proc of the 36th Int Conf on Machine Learning. New York: PMLR, 2019: 6438−6447, articleTitle=null, refAbstract=null), Reference(id=1329381595108192257, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Venkateswara H, Eusebio J, Chakraborty S, et al. Deep hashing network for unsupervised domain adaptation [C]// Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2017: 5385−5394, articleTitle=null, refAbstract=null), Reference(id=1329381595162718210, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Saito K, Watanabe K, Ushiku Y, et al. Maximum classifier discrepancy for unsupervised domain adaptation [C]// Proc of the 31st IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 3723−3732, articleTitle=null, refAbstract=null), Reference(id=1329381595271770116, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Hartigan J A, Hartigan P M. The dip test of unimodality[J]. The Annals of Statistics, 1985, 13(1): 70−84, articleTitle=null, refAbstract=null), Reference(id=1329381595359850501, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Hongyi, Cissé M, Dauphin Y N, et al. Mixup: Beyond empirical risk minimization [C/OL]// Proc of the 6th Int Conf on Learning Representations. 2018[2022-09-09].https://openreview.net/forum?id=r1Ddp1-Rb, articleTitle=null, refAbstract=null), Reference(id=1329381595422765062, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Sensoy M, Kaplan L, Kandemir M. Evidential deep learning to quantify classification uncertainty [C]// Proc of the 31st Int Conf on Neural Information Processing Systems. New York: Curran Associates, Inc, 2018: 3183−3193, articleTitle=null, refAbstract=null), Reference(id=1329381595523428359, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Peng Xingchao, Usman B, Kaushik N, et al. Visda: The visual domain adaptation challenge [J]. arXiv preprint, arXiv: 1710.06924, 2017, articleTitle=null, refAbstract=null), Reference(id=1329381595598925832, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Saenko K , Kulis B , Fritz M , et al. Adapting visual category models to new domains [C]// Proc of the 11th European Conf on Computer Vision: Part IV (ECCV’10). Berlin: Springer, 2010: 213–226, articleTitle=null, refAbstract=null), Reference(id=1329381595670229001, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Yuhua, Li Wen, Sakaridis C, et al. Domain adaptive faster R-CNN for object detection in the wild [C]// Proc of the 31st IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 3339−3348, articleTitle=null, refAbstract=null), Reference(id=1329381595745726474, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Saito K, Ushiku Y, Harada T, et al. Strong-weak distribution alignment for adaptive object detection [C]// Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2019: 6949−6958, articleTitle=null, refAbstract=null), Reference(id=1329381595821223947, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Hsu H K, Yao Chunhan, Tsai Y H, et al. Progressive domain adaptation for object detection [C]// Proc of the 20th IEEE Winter Conf on Applications of Computer Vision (WACV). Piscataway, NJ: IEEE, 2020: 738−746, articleTitle=null, refAbstract=null), Reference(id=1329381595913498636, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Cheng, Dou Qi, Chen Hao, et al. Synergistic image and feature adaptation: Towards cross-modality domain adaptation for medical image segmentation [C]// Proc of the 33rd AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2019: 865−872, articleTitle=null, refAbstract=null), Reference(id=1329381595980607501, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yuang, Zhang Wei, Wang Jun. Source-free domain adaptation for semantic segmentation [C]// Proc of the 34th IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2021: 1215−1224, articleTitle=null, refAbstract=null), Reference(id=1329381596081270798, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Bai Lubin, Du Shihong, Zhang Xiuyuan, et al. Domain adaptation for remote sensing image semantic segmentation: An integrated approach of contrastive learning and adversarial learning [J/OL]. IEEE Transactions on Geoscience and Remote Sensing, 2022[2022-09-09].https://ieeexplore.ieee.org/document/9857935/, articleTitle=null, refAbstract=null), Reference(id=1329381596160962575, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=He Yufan, Carass A, Zuo Lianrui, et al. Autoencoder based self-supervised test-time adaptation for medical image analysis[J]. Medical Image Analysis, 2021, 72(10): 102136, articleTitle=null, refAbstract=null), Reference(id=1329381596215488528, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Xiaofeng, Yoo C, Xing Fangxu, et al. Deep unsupervised domain adaptation: A review of recent advances and perspectives [J]. arXiv preprint, arXiv: 2208.07422, 2022, articleTitle=null, refAbstract=null), Reference(id=1329381596278403089, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Saltori C, Lathuilière S, Sebe N, et al. SF-UDA3D: Source-free unsupervised domain adaptation for lidar-based 3D object detection [C]// Proc of the 8th Int Conf on 3D Vision (3DV). Piscataway, NJ: IEEE, 2020: 771−780, articleTitle=null, refAbstract=null), Reference(id=1329381596341317650, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Peng Shuwen, Xi Xiaohuan, Wang Cheng, et al. Point-based multilevel domain adaptation for point cloud segmentation [J/OL]. IEEE Geoscience and Remote Sensing Letters, 2022[2022-09-09].https://ieeexplore.ieee.org/document/9272684, articleTitle=null, refAbstract=null), Reference(id=1329381596404232211, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Bian Yikai, Xie Jin, Qian Jianjun. Unsupervised domain adaptive point cloud semantic segmentation [C]// Proc of the 7th Asian Conf on Pattern Recognition (ACPR). Berlin: Springer, 2022: 285−298, articleTitle=null, refAbstract=null), Reference(id=1329381596475535380, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Pan Boxiao, Cao Zhangjie, Adeli E, et al. Adversarial cross-domain action recognition with co-attention [C]// Proc of the 34th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2020: 11815−11822, articleTitle=null, refAbstract=null), Reference(id=1329381596530061333, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Choi J, Sharma G, Schulter S, et al. Shuffle and attend: Video domain adaptation [C]// Proc of the 16th European Conf on Computer Vision (ECCV). Berlin: Springer, 2020: 678−695, articleTitle=null, refAbstract=null), Reference(id=1329381596601364502, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Minhung, Li Baopu, Bao Yingze, et al. Action segmentation with joint self-supervised temporal domain adaptation [C]// Proc of the 33rd IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2020: 9451−9460, articleTitle=null, refAbstract=null), Reference(id=1329381596664279063, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Deng Weijian, Zheng Liang, Ye Qixiang, et al. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification [C]// Proc of the 31st IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2018: 994−1003, articleTitle=null, refAbstract=null), Reference(id=1329381596727193624, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Mekhazni D, Bhuiyan A, Ekladious G, et al. Unsupervised domain adaptation in the dissimilarity space for person re-identification [C]// Proc of the 16th European Conf on Computer Vision (ECCV). Berlin: Springer, 2020: 159−174, articleTitle=null, refAbstract=null), Reference(id=1329381596790108185, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Qingchao, Liu Yang, Albanie S. Mind-the-gap! Unsupervised domain adaptation for text-video retrieval [C]// Proc of the 35th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2021: 1072−1080, articleTitle=null, refAbstract=null), Reference(id=1329381596853022746, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Pengfei, Li Leida, Wu Jinjian, et al. Unsupervised curriculum domain adaptation for no-reference video quality assessment [C]// Proc of the 18th IEEE/CVF Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2021: 5158−5167, articleTitle=null, refAbstract=null), Reference(id=1329381596911743003, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Tsenghung, Liao Yuanhong, Chuang Chingyao Y, et al. Show, adapt and tell: Adversarial training of cross-domain image captioner [C]// Proc of the 15th IEEE Int Conf on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2017: 521−530, articleTitle=null, refAbstract=null), Reference(id=1329381596970463260, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Wentian, Wu Xinxiao, Luo Jiebo. Cross-domain image captioning via cross-modal retrieval and model adaptation[J]. IEEE Transactions on Image Processing, 2021, 30: 1180−1192, articleTitle=null, refAbstract=null), Reference(id=1329381597041766429, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Ghosal D, Hazarika D, Roy A, et al. Kingdom: Knowledge-guided domain adaptation for sentiment analysis [C]// Proc of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2020: 3198−3210, articleTitle=null, refAbstract=null), Reference(id=1329381597100486686, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Ragab M, Eldele E, Chen Zhenghua, et al. Self-supervised autoregressive domain adaptation for time series data [J/OL]. IEEE Transactions on Neural Networks and Learning Systems, 2022[2022-09-09].https://ieeexplore.ieee.org/document/9804766, articleTitle=null, refAbstract=null), Reference(id=1329381597159206943, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Khurana S, Moritz N, Hori T, et al. Unsupervised domain adaptation for speech recognition via uncertainty driven self-training [C]// Proc of the 46th IEEE Int Conf on Acoustics, Speech and Signal Processing (ICASSP). Piscataway, NJ: IEEE, 2021: 6553−6557, articleTitle=null, refAbstract=null), Reference(id=1329381597226315808, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Tonutti M, Ruffaldi E, Cattaneo A, et al. Robust and subject-independent driving manoeuvre anticipation through domain-adversarial recurrent neural networks[J]. Robotics and Autonomous Systems, 2019, 115: 162−173, articleTitle=null, refAbstract=null), Reference(id=1329381597293424673, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yang, Zheng Wenming, Zong Yuan, et al. A bi-hemisphere domain adversarial neural network model for EEG emotion recognition[J]. IEEE Transactions on Affective Computing, 2021, 12(2): 494−504, articleTitle=null, refAbstract=null), Reference(id=1329381597364727842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Ouyang Cheng, Kamnitsas K, Biffi C, et al. Data efficient unsupervised domain adaptation for cross-modality image segmentation [C]// Proc of the 22nd Medical Image Computing and Computer Assisted Intervention (MICCAI) . Berlin: Springer, 2019: 669−677, articleTitle=null, refAbstract=null), Reference(id=1329381597427642403, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Xiaofeng, Xing Fangxu, Yang Chao, et al. Adapting off-the-shelf source segmenter for target medical image segmentation [C]// Proc of the 24th Medical Image Computing and Computer Assisted Intervention (MICCAI). Berlin: Springer, 2021: 549−559, articleTitle=null, refAbstract=null), Reference(id=1329381597498945572, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Jian, Li Xiangjie, Hu Gang, et al. Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNAseq analysis[J]. Nature Machine Intelligence, 2020, 2(10): 607−618, articleTitle=null, refAbstract=null), Reference(id=1329381597561860133, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Brbić M, Zitnik M, Wang Sheng, et al. MARS: Discovering novel cell types across heterogeneous single-cell experiments[J]. Nature Methods, 2020, 17(12): 1200−1206, articleTitle=null, refAbstract=null), Reference(id=1329381597628968998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Liang, Zhai Yuyao, He Qiuyan, et al. Integrating deep supervised, self-supervised and unsupervised learning for single-cell RNA-seq clustering and annotation [J]. Genes, 2020, 11(7): 792, articleTitle=null, refAbstract=null), Reference(id=1329381597691883559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Xie Kaikun, Huang Yu, Zeng Feng, et al. scAIDE: Clustering of large-scale single-cell RNA-seq data reveals putative and rare cell types[J]. NAR Genomics and Bioinformatics, 2020, 2(4): lqaa082, articleTitle=null, refAbstract=null), Reference(id=1329381597763186728, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Yuan Musu, Chen Liang, Deng Minghua. scMRA: A robust deep learning method to annotate scRNA-seq data with multiple reference datasets[J]. Bioinformatics, 2022, 3(1): 738−745, articleTitle=null, refAbstract=null), Reference(id=1329381597826101289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Chenling, Lopez R, Mehlman E, et al. Probabilistic harmonization and annotation of single-cell transcriptomics data with deep generative models[J]. Molecular Systems Biolny, 2021, 17(1): e9620, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329381586505675652, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, xref=1, ext=[AuthorCompanyExt(id=1329381586514064261, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586505675652, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Mathematical Sciences, Peking University, Beijing 100871), AuthorCompanyExt(id=1329381586522452870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586505675652, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1北京大学数学科学学院 北京 100871)]), AuthorCompany(id=1329381586581173127, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, xref=2, ext=[AuthorCompanyExt(id=1329381586589561736, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586581173127, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Center for Statistical Science, Peking University, Beijing 100871), AuthorCompanyExt(id=1329381586597950345, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586581173127, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2北京大学统计科学中心 北京 100871)]), AuthorCompany(id=1329381586669253514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, xref=3, ext=[AuthorCompanyExt(id=1329381586673447819, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586669253514, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3Center for Quantitative Biology, Peking University, Beijing 100871), AuthorCompanyExt(id=1329381586681836428, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, companyId=1329381586669253514, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3北京大学定量生物学中心 北京 100871)])], figs=[ArticleFig(id=1329381588032402339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 1, caption=
Classification of domain adaptation by the relationship of label sets of source domain and target domain, figureFileSmall=tmIEgcwlgdIwKJ9rSTkCUw==, figureFileBig=qsuU8PzHzCqbVv8WZEr9CQ==, tableContent=null), ArticleFig(id=1329381588112094116, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图1, caption=
按源域和目标域标签集合相对关系对域适应问题进行分类, figureFileSmall=tmIEgcwlgdIwKJ9rSTkCUw==, figureFileBig=qsuU8PzHzCqbVv8WZEr9CQ==, tableContent=null), ArticleFig(id=1329381588284060581, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 2, caption=
The general network structure, adversarial idea and inference method of adversarial methods, figureFileSmall=cs2YPnaxxDdhicKMuUWwAQ==, figureFileBig=dJtckqkngKFUxdcW82KIGQ==, tableContent=null), ArticleFig(id=1329381588346975142, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图2, caption=
对抗类方法的一般网络架构、对抗思想与预测方法, figureFileSmall=cs2YPnaxxDdhicKMuUWwAQ==, figureFileBig=dJtckqkngKFUxdcW82KIGQ==, tableContent=null), ArticleFig(id=1329381588435055527, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 3, caption=
The network structure of autoencoder, figureFileSmall=/LQ2LsmAEcbYa2t7kYqcJA==, figureFileBig=tS3PlsVlaVBYmiXyQrMhbA==, tableContent=null), ArticleFig(id=1329381588493775784, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图3, caption=
自编码网络结构, figureFileSmall=/LQ2LsmAEcbYa2t7kYqcJA==, figureFileBig=tS3PlsVlaVBYmiXyQrMhbA==, tableContent=null), ArticleFig(id=1329381588556690345, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 4, caption=
The idea diagram of contrastive learning, figureFileSmall=Ju7DXBKYCsnoo1TdWhp3Cw==, figureFileBig=Mtu9hGjesqFQDZyCbmSLWw==, tableContent=null), ArticleFig(id=1329381588627993514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图4, caption=
对比学习概念图, figureFileSmall=Ju7DXBKYCsnoo1TdWhp3Cw==, figureFileBig=Mtu9hGjesqFQDZyCbmSLWw==, tableContent=null), ArticleFig(id=1329381588707685291, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 5, caption=
Neighborhood clustering: Find the most similar sample or centroid to approach, figureFileSmall=sOZU6ouQnpK2eYklZj5urg==, figureFileBig=KFqAPXRGO0tE+BSM0aodbA==, tableContent=null), ArticleFig(id=1329381588799959980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图5, caption=
寻找最相似样本或类中心来靠近的邻域聚类, figureFileSmall=sOZU6ouQnpK2eYklZj5urg==, figureFileBig=KFqAPXRGO0tE+BSM0aodbA==, tableContent=null), ArticleFig(id=1329381588862874541, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 6, caption=
Separating target domain samples by entropy for training, figureFileSmall=M+n1i+GzsAzLYItEF7wDDQ==, figureFileBig=hI2ivULhZWGShH9/el2VCg==, tableContent=null), ArticleFig(id=1329381588913206190, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图6, caption=
依据熵划分目标域样本以训练, figureFileSmall=M+n1i+GzsAzLYItEF7wDDQ==, figureFileBig=hI2ivULhZWGShH9/el2VCg==, tableContent=null), ArticleFig(id=1329381588971926447, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 7, caption=
Find MNN to reduce domain bias and transfer labels, figureFileSmall=0biQyXxYpkCvdASagEJ4hg==, figureFileBig=CyNZLEa1to7zI5fNaLfXqA==, tableContent=null), ArticleFig(id=1329381589039035312, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图7, caption=
寻找互近邻消除域间差异进行标记, figureFileSmall=0biQyXxYpkCvdASagEJ4hg==, figureFileBig=CyNZLEa1to7zI5fNaLfXqA==, tableContent=null), ArticleFig(id=1329381589093561265, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 8, caption=
Ideal result and realistic problems of adversarial methods, figureFileSmall=qHz2a1WkgOyfkaCBKk/9oQ==, figureFileBig=7ubarxwCrnh7O9PVOkeQzQ==, tableContent=null), ArticleFig(id=1329381589156475826, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图8, caption=
对抗学习的理想效果与现实问题, figureFileSmall=qHz2a1WkgOyfkaCBKk/9oQ==, figureFileBig=7ubarxwCrnh7O9PVOkeQzQ==, tableContent=null), ArticleFig(id=1329381589219390387, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 9, caption=
Sample numbers of each class when each domain contains its private classes using VisDA, figureFileSmall=nk6WYFv+zwGwIQHitSdrTw==, figureFileBig=gNMOIkPUPcE312HwmTHuuQ==, tableContent=null), ArticleFig(id=1329381589278110644, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图9, caption=
使用VisDA时每种域均含私有类的各类样本数, figureFileSmall=nk6WYFv+zwGwIQHitSdrTw==, figureFileBig=gNMOIkPUPcE312HwmTHuuQ==, tableContent=null), ArticleFig(id=1329381589345219509, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 10, caption=
Maximum probability predicted by the classifier trained only using source labels on VisDA, figureFileSmall=2bof7peqK9cUeAeDqN3y2A==, figureFileBig=5U0XuJTmlAw7HdCM08KDLw==, tableContent=null), ArticleFig(id=1329381589441688502, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图10, caption=
以VisDA为例仅用源域标签训练分类器得到的预测最大概率, figureFileSmall=2bof7peqK9cUeAeDqN3y2A==, figureFileBig=5U0XuJTmlAw7HdCM08KDLw==, tableContent=null), ArticleFig(id=1329381589521380279, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 11, caption=
Demo of merging split images and mixing up images in raw feature space, figureFileSmall=X1NTrMCdS6saGotAo/DKAQ==, figureFileBig=4Ro4eQSm/5altBXRMiN9gw==, tableContent=null), ArticleFig(id=1329381589588489144, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图11, caption=
原特征空间中图片的拼接与混合示例, figureFileSmall=X1NTrMCdS6saGotAo/DKAQ==, figureFileBig=4Ro4eQSm/5altBXRMiN9gw==, tableContent=null), ArticleFig(id=1329381589651403705, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Figure 12, caption=
Entropy of target samples when only training with source data on VisDA, figureFileSmall=1JWjz7WOekPevTMZnGRJrQ==, figureFileBig=BUJbt4cohSE3RoN0kYTt0A==, tableContent=null), ArticleFig(id=1329381589726901178, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=图12, caption=
以VisDA为例仅用源域数据训练后的目标样本熵, figureFileSmall=1JWjz7WOekPevTMZnGRJrQ==, figureFileBig=BUJbt4cohSE3RoN0kYTt0A==, tableContent=null), ArticleFig(id=1329381589806592955, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 1, caption=
Strategies and Unknown Classes Detection Ways Used in Adversarial UniDA Methods
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 策略 | 未知类判别方法 |
|---|
多分 类器 | 分类器含 未知类 | 用类 中心 | 熵分离 样本 | 邻域 聚类 | 互近邻 | 对比 学习 | 数据 增广 | 样本 混合 | 重构 网络 | 其他 |
|---|
| UAN[7] | | | | | | | | | | | | 样本权重 |
| UMAN[12] | | | | | | | | | | | | 样本权重 |
| ADCL[14] | | | | | | | | | | | Gradient Embeddings | 样本权重 |
| 文献[15] | | | | | | | | | | | | 概率估计 |
| CMU[16] | √ | | | | | | | | | | | 样本权重 |
| I-UAN[17] | | | | | | | | | | | | 样本权重 |
| DCN[18] | | | | | | | √ | | | | | 样本权重 |
| 文献[19] | | | | | | | | | | √ | | outlier分类器 |
| 文献[20] | | | | | | | | | | | | $ s\left(x\right) $ |
| HFDN[21] | | | | | | | | | | √ | 分层解耦 | 样本权重 |
| GATE[22] | | √ | | | | √ | √ | | √ | | | 分类器 |
| Uni3DA[23] | | | | | | | | | | | 自监督权重优化 | 样本权重 |
), ArticleFig(id=1329381589886284732, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表1, caption=
对抗类通用域适应方法使用的策略及未知类判别方法
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 策略 | 未知类判别方法 |
|---|
多分 类器 | 分类器含 未知类 | 用类 中心 | 熵分离 样本 | 邻域 聚类 | 互近邻 | 对比 学习 | 数据 增广 | 样本 混合 | 重构 网络 | 其他 |
|---|
| UAN[7] | | | | | | | | | | | | 样本权重 |
| UMAN[12] | | | | | | | | | | | | 样本权重 |
| ADCL[14] | | | | | | | | | | | Gradient Embeddings | 样本权重 |
| 文献[15] | | | | | | | | | | | | 概率估计 |
| CMU[16] | √ | | | | | | | | | | | 样本权重 |
| I-UAN[17] | | | | | | | | | | | | 样本权重 |
| DCN[18] | | | | | | | √ | | | | | 样本权重 |
| 文献[19] | | | | | | | | | | √ | | outlier分类器 |
| 文献[20] | | | | | | | | | | | | $ s\left(x\right) $ |
| HFDN[21] | | | | | | | | | | √ | 分层解耦 | 样本权重 |
| GATE[22] | | √ | | | | √ | √ | | √ | | | 分类器 |
| Uni3DA[23] | | | | | | | | | | | 自监督权重优化 | 样本权重 |
), ArticleFig(id=1329381590024696765, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 2, caption=
Strategies and Unknown Classes Detection Ways Used in Non-Adversarial UniDA Methods
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 策略 | 未知类判别方法 |
|---|
多分 类器 | 分类器含 未知类 | 用类 中心 | 用熵分 离样本 | 邻域 聚类 | 互近邻 | 对比 学习 | 数据 增广 | 样本 混合 | 重构 网络 | 其他 |
|---|
| USFDA[9] | | √ | | | | | | | | | 模拟负样本 | 分类器 |
| UMAD[10] | √ | | | | | | | | √ | | | iscore |
| UB2DA[11] | | | √ | √ | | | | | | | 邻域一致性 | 熵 |
| 文献[13] | √ | | | √ | | | | | | | 利用预测差异 | 熵 |
| DANCE[24] | | | √ | √ | √ | | | | | | | 熵 |
| 文献[25] | | | √ | √ | √ | | √ | √ | | | | 熵 |
| 文献[26] | | | √ | √ | √ | | | √ | | | | 熵 |
| DCC[27] | | | √ | | | √ | √ | | | | | 目标域类中心 |
| MATHS[28] | | | √ | | | √ | √ | | | | 统计检验未知类 | 预测概率 |
| OVANet[29] | √ | | | | | | | | | | | 多维和二元分类器 |
| TNT[30] | | | | | | √ | √ | | | | EDL模型 | total evidence score |
), ArticleFig(id=1329381590091805630, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表2, caption=
非对抗类通用域适应方法使用的策略和未知类判别方法
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 策略 | 未知类判别方法 |
|---|
多分 类器 | 分类器含 未知类 | 用类 中心 | 用熵分 离样本 | 邻域 聚类 | 互近邻 | 对比 学习 | 数据 增广 | 样本 混合 | 重构 网络 | 其他 |
|---|
| USFDA[9] | | √ | | | | | | | | | 模拟负样本 | 分类器 |
| UMAD[10] | √ | | | | | | | | √ | | | iscore |
| UB2DA[11] | | | √ | √ | | | | | | | 邻域一致性 | 熵 |
| 文献[13] | √ | | | √ | | | | | | | 利用预测差异 | 熵 |
| DANCE[24] | | | √ | √ | √ | | | | | | | 熵 |
| 文献[25] | | | √ | √ | √ | | √ | √ | | | | 熵 |
| 文献[26] | | | √ | √ | √ | | | √ | | | | 熵 |
| DCC[27] | | | √ | | | √ | √ | | | | | 目标域类中心 |
| MATHS[28] | | | √ | | | √ | √ | | | | 统计检验未知类 | 预测概率 |
| OVANet[29] | √ | | | | | | | | | | | 多维和二元分类器 |
| TNT[30] | | | | | | √ | √ | | | | EDL模型 | total evidence score |
), ArticleFig(id=1329381590167303103, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 3, caption=
Adversarial Loss of Adversarial UniDA Methods
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 对抗损失 |
|---|
| UAN[7] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}{w}^{\mathrm{t}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| UMAN[12] | $-\dfrac{1}{M}\mathop { {\sum } }\limits_{i=1}^{M}{E}_{x\sim {P}_{i}\left(x\right)}{w}^{\mathrm{s} }\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t} }\left(x\right)}{w}^{\mathrm{t} }\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right)$① |
| ADCL[14] | $ {E}_{x\in {\mathcal{D}}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right)+{E}_{x\in {\mathcal{D}}_{\mathrm{U}\mathrm{T}}}\left[{1}_{{w}^{\mathrm{t}}\left({x}^{\mathrm{t}}\right) > {w}_{\alpha }\left(t\right)}\mathrm{ln}D\left(G\left(x\right)\right)\right]+{E}_{x\in {\mathcal{D}}_{\mathrm{L}\mathrm{T}},y\in {L}_{\mathrm{s}}}\mathrm{ln}D\left(G\left(x\right)\right) $② |
| 文献[15] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}w\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}w\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| Uni3DA[23] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}{w}^{\mathrm{t}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| CMU[16] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}{w}^{\mathrm{t}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| I-UAN[17] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}{w}^{\mathrm{t}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| DCN[18] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}w\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}w\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| 文献[19] | $ -{\beta }_{\mathrm{s}}{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{\beta }_{\mathrm{t}}{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}{w}^{\mathrm{t}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| 文献[20] | $-\mathop { {\sum } }\limits_{ {x\sim{P}_{\mathrm{s} } \left(x\right)} }\mathrm{ln}D\left(G\left(x\right)\right)-\mathop { {\sum } }\limits_{x\sim {P}_{\mathrm{t} }\left(x\right)}\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right)$ |
| HFDN[21] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}\mathrm{ln}D\left({f}_{\mathrm{d}\mathrm{d}}^{\mathrm{s}}\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}\mathrm{ln}\left(1-D\left({f}_{\mathrm{d}\mathrm{d}}^{\mathrm{t}}\right)\right) $③ |
| GATE[22] | $ -{E}_{x\in {\mathcal{M}}_{\mathrm{s}}\left(x\right)}\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\in {\mathcal{M}}_{\mathrm{t}}\left(x\right)}\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $④ |
), ArticleFig(id=1329381590234411968, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表3, caption=
对抗类通用域适应方法的对抗损失
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 对抗损失 |
|---|
| UAN[7] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}{w}^{\mathrm{t}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| UMAN[12] | $-\dfrac{1}{M}\mathop { {\sum } }\limits_{i=1}^{M}{E}_{x\sim {P}_{i}\left(x\right)}{w}^{\mathrm{s} }\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t} }\left(x\right)}{w}^{\mathrm{t} }\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right)$① |
| ADCL[14] | $ {E}_{x\in {\mathcal{D}}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right)+{E}_{x\in {\mathcal{D}}_{\mathrm{U}\mathrm{T}}}\left[{1}_{{w}^{\mathrm{t}}\left({x}^{\mathrm{t}}\right) > {w}_{\alpha }\left(t\right)}\mathrm{ln}D\left(G\left(x\right)\right)\right]+{E}_{x\in {\mathcal{D}}_{\mathrm{L}\mathrm{T}},y\in {L}_{\mathrm{s}}}\mathrm{ln}D\left(G\left(x\right)\right) $② |
| 文献[15] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}w\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}w\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| Uni3DA[23] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}{w}^{\mathrm{t}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| CMU[16] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}{w}^{\mathrm{t}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| I-UAN[17] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}{w}^{\mathrm{t}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| DCN[18] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}w\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}w\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| 文献[19] | $ -{\beta }_{\mathrm{s}}{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}{w}^{\mathrm{s}}\left(x\right)\mathrm{ln}D\left(G\left(x\right)\right)-{\beta }_{\mathrm{t}}{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}{w}^{\mathrm{t}}\left(x\right)\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $ |
| 文献[20] | $-\mathop { {\sum } }\limits_{ {x\sim{P}_{\mathrm{s} } \left(x\right)} }\mathrm{ln}D\left(G\left(x\right)\right)-\mathop { {\sum } }\limits_{x\sim {P}_{\mathrm{t} }\left(x\right)}\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right)$ |
| HFDN[21] | $ -{E}_{x\sim {P}_{\mathrm{s}}\left(x\right)}\mathrm{ln}D\left({f}_{\mathrm{d}\mathrm{d}}^{\mathrm{s}}\right)-{E}_{x\sim {P}_{\mathrm{t}}\left(x\right)}\mathrm{ln}\left(1-D\left({f}_{\mathrm{d}\mathrm{d}}^{\mathrm{t}}\right)\right) $③ |
| GATE[22] | $ -{E}_{x\in {\mathcal{M}}_{\mathrm{s}}\left(x\right)}\mathrm{ln}D\left(G\left(x\right)\right)-{E}_{x\in {\mathcal{M}}_{\mathrm{t}}\left(x\right)}\mathrm{ln}\left(1-D\left(G\left(x\right)\right)\right) $④ |
), ArticleFig(id=1329381590309909441, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 4, caption=
Weights in Adversarial Loss and Unknown Classes Detection Ways of Adversarial UniDA Methods
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | $ {w}^{\mathrm{s}}\left(x\right) $ | $ {w}^{\mathrm{t}}\left(x\right) $ | 未知类判别 |
|---|
| UAN[7] | $\frac{H\left(\hat{\boldsymbol{p} }\right)}{\mathrm{ln}{K}_{\mathrm{s} } }-{\hat{d} }^{{'}}\left(x\right)$② | ${\hat{d} }^{{'} }\left(x\right)-\frac{H\left(\hat{\boldsymbol{p} }\right)}{\mathrm{ln}{K}_{\mathrm{s} } }$ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| UMAN[12] | $ {\boldsymbol{V}}_{\mathrm{T}\mathrm{P}\mathrm{M}\mathrm{R}}\left[{y}^{\mathrm{s}}\right] $ | $ {\hat{m}}_{\mathrm{f}}\left(x\right){\boldsymbol{V}}_{\mathrm{T}\mathrm{P}\mathrm{M}\mathrm{R}}\left[{\hat{y}}^{\mathrm{t}}\right] $③ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| ADCL[14] | $ {\boldsymbol{V}}_{{y}^{\mathrm{s}}} $,$\boldsymbol{V}={{avg} }_{ {w}^{\mathrm{t} }\left({x}^{\mathrm{t} }\right) > {w}_{\alpha }\left(t\right)}{\hat{y} }^{\mathrm{t} }$ | $ \mathrm{max}\hat{\boldsymbol{p}}\left(x\right)+d\left(x\right) $ | $ {w}^{\mathrm{t}}\left(x\right)\le {w}_{\alpha }\left(t\right) $ |
| 文献[15] | $ P\left(x\in {L}_{\mathrm{s}}\cap {L}_{\mathrm{t}}\right) $ | $ P\left(x\in {L}_{\mathrm{s}}\cap {L}_{\mathrm{t}}\right) $ | $ P\left(x\in {L}_{\mathrm{s}}\cap {L}_{\mathrm{t}}\right)\le \frac{1}{2} $ |
| Uni3DA[23] | $ \frac{H\left(\hat{\boldsymbol{p}}\right)}{\mathrm{ln}{K}_{\mathrm{s}}}-{\hat{d}}^{{'} }\left(x\right) $ | $ {\hat{d}}^{{'} }\left(x\right)-\frac{H\left(\hat{\boldsymbol{p}}\right)}{\mathrm{ln}{K}_{\mathrm{s}}} $ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| CMU[16] | ${\boldsymbol{V} }_{ {y}^{\mathrm{s} } },\boldsymbol{V}={{avg} }_{ {w}^{\mathrm{t} }\left({x}^{\mathrm{t} }\right) > {w}_{0} }{\hat{y} }^{\mathrm{t} }$ | $\dfrac{\left(1-{w}_{\text{ent} }\right)+\left(1-{w}_{\text{cons} }\right)+{w}_{\text{conf} } }{3}$ | $ {w}^{\mathrm{t}}\left(x\right)\le {w}_{0} $ |
| I-UAN[17] | $ {\boldsymbol{V}}_{\mathrm{T}\mathrm{P}\mathrm{M}\mathrm{R}}\left[{y}^{s}\right] $ | $ \mathrm{max}\hat{\boldsymbol{p}}\left(x\right) $ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| DCN[18] | $ \mathrm{max}\hat{\boldsymbol{p}}\left(x\right)+d\left(x\right)+\frac{H\left(\hat{\boldsymbol{p}}\left(x\right)\right)}{\mathrm{ln}{K}_{\mathrm{s}}} $ | $ \mathrm{max}\hat{\boldsymbol{p}}\left(x\right)+d\left(x\right)+\frac{H\left(\hat{\boldsymbol{p}}\left(x\right)\right)}{\mathrm{ln}{K}_{\mathrm{s}}} $ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| 文献[19] | $ {\hat{w}}^{\mathrm{s},\mathrm{d}}+{\hat{w}}^{\mathrm{s},\mathrm{e}} $④ | $ {\hat{w}}^{\mathrm{t},\mathrm{d}}+{\hat{w}}^{\mathrm{t},\mathrm{e}} $ | Outlier Identifier |
| 文献[20] | $ 1 $ | $ 1 $ | $ s\left(x\right)\le {s}_{\beta }\left(t\right) $, $ s\left(x\right)=\mathrm{max}\hat{\boldsymbol{p}}\left(x\right)+d\left(x\right) $⑤ |
| HFDN[21] | $ {\frac{D\left(R\left({f}_{\mathrm{d}\mathrm{c}},0\right)\right)}{{E}_{x\in {\mathcal{D}}_{\mathrm{s}}\left(x\right)}D\left(R\left({f}_{\mathrm{d}\mathrm{c}},0\right)\right)}}^{\mathrm{⑥}} $ | $ \frac{D\left(R\left({f}_{\mathrm{d}\mathrm{c}},0\right)\right)}{{E}_{x\in {\mathcal{D}}_{\mathrm{t}}\left(x\right)}D\left(R\left({f}_{\mathrm{d}\mathrm{c}},0\right)\right)} $ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| GATE[22] | $ {1}_{\{x\in {\mathcal{M}}_{\mathrm{s}}\}} $ | $ {1}_{\{x\in {\mathcal{M}}_{\mathrm{t}}\}} $ | $ {K}_{\mathrm{s}}+1 $维分类器 |
), ArticleFig(id=1329381590397989826, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表4, caption=
对抗类通用域适应方法对抗损失中的权重及未知类判别方法①
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | $ {w}^{\mathrm{s}}\left(x\right) $ | $ {w}^{\mathrm{t}}\left(x\right) $ | 未知类判别 |
|---|
| UAN[7] | $\frac{H\left(\hat{\boldsymbol{p} }\right)}{\mathrm{ln}{K}_{\mathrm{s} } }-{\hat{d} }^{{'}}\left(x\right)$② | ${\hat{d} }^{{'} }\left(x\right)-\frac{H\left(\hat{\boldsymbol{p} }\right)}{\mathrm{ln}{K}_{\mathrm{s} } }$ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| UMAN[12] | $ {\boldsymbol{V}}_{\mathrm{T}\mathrm{P}\mathrm{M}\mathrm{R}}\left[{y}^{\mathrm{s}}\right] $ | $ {\hat{m}}_{\mathrm{f}}\left(x\right){\boldsymbol{V}}_{\mathrm{T}\mathrm{P}\mathrm{M}\mathrm{R}}\left[{\hat{y}}^{\mathrm{t}}\right] $③ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| ADCL[14] | $ {\boldsymbol{V}}_{{y}^{\mathrm{s}}} $,$\boldsymbol{V}={{avg} }_{ {w}^{\mathrm{t} }\left({x}^{\mathrm{t} }\right) > {w}_{\alpha }\left(t\right)}{\hat{y} }^{\mathrm{t} }$ | $ \mathrm{max}\hat{\boldsymbol{p}}\left(x\right)+d\left(x\right) $ | $ {w}^{\mathrm{t}}\left(x\right)\le {w}_{\alpha }\left(t\right) $ |
| 文献[15] | $ P\left(x\in {L}_{\mathrm{s}}\cap {L}_{\mathrm{t}}\right) $ | $ P\left(x\in {L}_{\mathrm{s}}\cap {L}_{\mathrm{t}}\right) $ | $ P\left(x\in {L}_{\mathrm{s}}\cap {L}_{\mathrm{t}}\right)\le \frac{1}{2} $ |
| Uni3DA[23] | $ \frac{H\left(\hat{\boldsymbol{p}}\right)}{\mathrm{ln}{K}_{\mathrm{s}}}-{\hat{d}}^{{'} }\left(x\right) $ | $ {\hat{d}}^{{'} }\left(x\right)-\frac{H\left(\hat{\boldsymbol{p}}\right)}{\mathrm{ln}{K}_{\mathrm{s}}} $ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| CMU[16] | ${\boldsymbol{V} }_{ {y}^{\mathrm{s} } },\boldsymbol{V}={{avg} }_{ {w}^{\mathrm{t} }\left({x}^{\mathrm{t} }\right) > {w}_{0} }{\hat{y} }^{\mathrm{t} }$ | $\dfrac{\left(1-{w}_{\text{ent} }\right)+\left(1-{w}_{\text{cons} }\right)+{w}_{\text{conf} } }{3}$ | $ {w}^{\mathrm{t}}\left(x\right)\le {w}_{0} $ |
| I-UAN[17] | $ {\boldsymbol{V}}_{\mathrm{T}\mathrm{P}\mathrm{M}\mathrm{R}}\left[{y}^{s}\right] $ | $ \mathrm{max}\hat{\boldsymbol{p}}\left(x\right) $ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| DCN[18] | $ \mathrm{max}\hat{\boldsymbol{p}}\left(x\right)+d\left(x\right)+\frac{H\left(\hat{\boldsymbol{p}}\left(x\right)\right)}{\mathrm{ln}{K}_{\mathrm{s}}} $ | $ \mathrm{max}\hat{\boldsymbol{p}}\left(x\right)+d\left(x\right)+\frac{H\left(\hat{\boldsymbol{p}}\left(x\right)\right)}{\mathrm{ln}{K}_{\mathrm{s}}} $ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| 文献[19] | $ {\hat{w}}^{\mathrm{s},\mathrm{d}}+{\hat{w}}^{\mathrm{s},\mathrm{e}} $④ | $ {\hat{w}}^{\mathrm{t},\mathrm{d}}+{\hat{w}}^{\mathrm{t},\mathrm{e}} $ | Outlier Identifier |
| 文献[20] | $ 1 $ | $ 1 $ | $ s\left(x\right)\le {s}_{\beta }\left(t\right) $, $ s\left(x\right)=\mathrm{max}\hat{\boldsymbol{p}}\left(x\right)+d\left(x\right) $⑤ |
| HFDN[21] | $ {\frac{D\left(R\left({f}_{\mathrm{d}\mathrm{c}},0\right)\right)}{{E}_{x\in {\mathcal{D}}_{\mathrm{s}}\left(x\right)}D\left(R\left({f}_{\mathrm{d}\mathrm{c}},0\right)\right)}}^{\mathrm{⑥}} $ | $ \frac{D\left(R\left({f}_{\mathrm{d}\mathrm{c}},0\right)\right)}{{E}_{x\in {\mathcal{D}}_{\mathrm{t}}\left(x\right)}D\left(R\left({f}_{\mathrm{d}\mathrm{c}},0\right)\right)} $ | $ {w}^{\mathrm{t}}\left(x\right) < {w}_{0} $ |
| GATE[22] | $ {1}_{\{x\in {\mathcal{M}}_{\mathrm{s}}\}} $ | $ {1}_{\{x\in {\mathcal{M}}_{\mathrm{t}}\}} $ | $ {K}_{\mathrm{s}}+1 $维分类器 |
), ArticleFig(id=1329381590507041731, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 5, caption=
Average Accuracy of Each Method over OfficeHome and VisDA Under CDA %
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (65/0/0) | VisDA (12/0/0) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 14.6 | 20.6 | 22.8 | 16.3 | 18.9 | 17.4 | 23.6 | 19.8 | 29.4 | 27.2 | 19.0 | 30.1 | 21.6 | 61.1 |
| CMU[16] | 16.9 | 20.1 | 27.6 | 10.5 | 21.9 | 25.8 | 21.1 | 21.0 | 37.2 | 33.1 | 27.7 | 46.7 | 25.8 | 23.0 |
| I-UAN[17] | 27.6 | 40.9 | 49.0 | 26.4 | 34.3 | 35.2 | 34.8 | 27.4 | 52.1 | 43.9 | 31.4 | 57.1 | 38.3 | 49.2 |
| DANCE[24] | 54.6 | 75.2 | 76.2 | 58.9 | 70.3 | 72.1 | 60.0 | 52.4 | 78.6 | 68.7 | 59.5 | 82.2 | 74.4 | 72.1 |
| DCC[27] | 37.4 | 43.4 | 67.6 | 30.9 | 56.1 | 41.3 | 44.1 | 29.2 | 70.1 | 42.9 | 36.9 | 75.2 | 57.8 | 47.5 |
| OVANet[29] | 34.3 | 54.4 | 64.5 | 34.5 | 49.9 | 53.5 | 32.3 | 25.8 | 59.8 | 50.5 | 35.0 | 69.5 | 55.8 | 28.2 |
| 文献[13] (clean) | 53.9 | 70.8 | 74.9 | 58.1 | 68.6 | 70.4 | 56.6 | 51.6 | 77.0 | 67.6 | 57.8 | 81.1 | 67.4 | 71.1 |
| 否 | UB2DA[11](SF) | 41.9 | 59.6 | 49.0 | 46.2 | 55.1 | 55.3 | 46.6 | 34.7 | 60.5 | 60.7 | 41.2 | 62.6 | 51.1 | 7.3 |
| UB2DA[11](BX) | 36.1 | 57.3 | 63.5 | 34.2 | 52.3 | 55.3 | 39.0 | 28.8 | 61.0 | 49.7 | 38.0 | 67.3 | 48.5 | 11.7 |
), ArticleFig(id=1329381590578344900, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表5, caption=
CDA情形下各方法在OfficeHome和VisDA上的平均准确度
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (65/0/0) | VisDA (12/0/0) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 14.6 | 20.6 | 22.8 | 16.3 | 18.9 | 17.4 | 23.6 | 19.8 | 29.4 | 27.2 | 19.0 | 30.1 | 21.6 | 61.1 |
| CMU[16] | 16.9 | 20.1 | 27.6 | 10.5 | 21.9 | 25.8 | 21.1 | 21.0 | 37.2 | 33.1 | 27.7 | 46.7 | 25.8 | 23.0 |
| I-UAN[17] | 27.6 | 40.9 | 49.0 | 26.4 | 34.3 | 35.2 | 34.8 | 27.4 | 52.1 | 43.9 | 31.4 | 57.1 | 38.3 | 49.2 |
| DANCE[24] | 54.6 | 75.2 | 76.2 | 58.9 | 70.3 | 72.1 | 60.0 | 52.4 | 78.6 | 68.7 | 59.5 | 82.2 | 74.4 | 72.1 |
| DCC[27] | 37.4 | 43.4 | 67.6 | 30.9 | 56.1 | 41.3 | 44.1 | 29.2 | 70.1 | 42.9 | 36.9 | 75.2 | 57.8 | 47.5 |
| OVANet[29] | 34.3 | 54.4 | 64.5 | 34.5 | 49.9 | 53.5 | 32.3 | 25.8 | 59.8 | 50.5 | 35.0 | 69.5 | 55.8 | 28.2 |
| 文献[13] (clean) | 53.9 | 70.8 | 74.9 | 58.1 | 68.6 | 70.4 | 56.6 | 51.6 | 77.0 | 67.6 | 57.8 | 81.1 | 67.4 | 71.1 |
| 否 | UB2DA[11](SF) | 41.9 | 59.6 | 49.0 | 46.2 | 55.1 | 55.3 | 46.6 | 34.7 | 60.5 | 60.7 | 41.2 | 62.6 | 51.1 | 7.3 |
| UB2DA[11](BX) | 36.1 | 57.3 | 63.5 | 34.2 | 52.3 | 55.3 | 39.0 | 28.8 | 61.0 | 49.7 | 38.0 | 67.3 | 48.5 | 11.7 |
), ArticleFig(id=1329381590658036677, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 6, caption=
Average Accuracy of Each Method over OfficeHome and VisDA Under PDA %
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (25/40/0) | VisDA (6/6/0) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 23.2 | 16.4 | 10.4 | 15.7 | 20.6 | 21.5 | 22.1 | 13.1 | 20.7 | 25.4 | 22.7 | 20.2 | 19.3 | 40.2 |
| CMU[16] | 24.1 | 30.8 | 37.8 | 13.1 | 21.6 | 25.0 | 22.9 | 29.7 | 42.4 | 36.9 | 36.4 | 51.4 | 31.0 | 24.6 |
| I-UAN[17] | 33.3 | 48.6 | 52.8 | 34.0 | 36.4 | 38.8 | 40.8 | 32.6 | 54.0 | 49.0 | 37.0 | 59.7 | 43.1 | 55.6 |
| DANCE[24] | 55.5 | 73.1 | 82.8 | 64.2 | 68.1 | 76.8 | 62.8 | 49.0 | 83.5 | 72.1 | 56.5 | 81.7 | 68.8 | 80.7 |
| DCC[27] | 50.3 | 68.3 | 80.4 | 49.9 | 60.4 | 73.1 | 55.3 | 24.8 | 69.2 | 28.1 | 46.4 | 80.6 | 57.2 | 38.4 |
| OVANet[29] | 34.8 | 56.0 | 68.5 | 33.6 | 46.3 | 49.6 | 33.0 | 26.2 | 58.3 | 53.0 | 37.9 | 68.8 | 47.2 | 25.5 |
| 文献[13](clean) | 43.1 | 61.6 | 70.2 | 37.4 | 51.2 | 60.3 | 27.4 | 32.3 | 65.7 | 49.8 | 38.9 | 72.6 | 50.9 | 73.4 |
| 否 | UB2DA[11](SF) | 42.3 | 62.5 | 66.5 | 45.8 | 52.9 | 55.2 | 50.1 | 37.2 | 64.9 | 63.8 | 44.4 | 71.1 | 54.7 | 28.3 |
| UB2DA[11](BX) | 36.8 | 59.3 | 63.2 | 34.7 | 50.9 | 53.2 | 36.9 | 29.1 | 57.7 | 48.8 | 39.3 | 66.7 | 48.1 | 33.8 |
), ArticleFig(id=1329381590767088582, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表6, caption=
PDA情形下各方法在OfficeHome和VisDA上的平均准确度
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (25/40/0) | VisDA (6/6/0) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 23.2 | 16.4 | 10.4 | 15.7 | 20.6 | 21.5 | 22.1 | 13.1 | 20.7 | 25.4 | 22.7 | 20.2 | 19.3 | 40.2 |
| CMU[16] | 24.1 | 30.8 | 37.8 | 13.1 | 21.6 | 25.0 | 22.9 | 29.7 | 42.4 | 36.9 | 36.4 | 51.4 | 31.0 | 24.6 |
| I-UAN[17] | 33.3 | 48.6 | 52.8 | 34.0 | 36.4 | 38.8 | 40.8 | 32.6 | 54.0 | 49.0 | 37.0 | 59.7 | 43.1 | 55.6 |
| DANCE[24] | 55.5 | 73.1 | 82.8 | 64.2 | 68.1 | 76.8 | 62.8 | 49.0 | 83.5 | 72.1 | 56.5 | 81.7 | 68.8 | 80.7 |
| DCC[27] | 50.3 | 68.3 | 80.4 | 49.9 | 60.4 | 73.1 | 55.3 | 24.8 | 69.2 | 28.1 | 46.4 | 80.6 | 57.2 | 38.4 |
| OVANet[29] | 34.8 | 56.0 | 68.5 | 33.6 | 46.3 | 49.6 | 33.0 | 26.2 | 58.3 | 53.0 | 37.9 | 68.8 | 47.2 | 25.5 |
| 文献[13](clean) | 43.1 | 61.6 | 70.2 | 37.4 | 51.2 | 60.3 | 27.4 | 32.3 | 65.7 | 49.8 | 38.9 | 72.6 | 50.9 | 73.4 |
| 否 | UB2DA[11](SF) | 42.3 | 62.5 | 66.5 | 45.8 | 52.9 | 55.2 | 50.1 | 37.2 | 64.9 | 63.8 | 44.4 | 71.1 | 54.7 | 28.3 |
| UB2DA[11](BX) | 36.8 | 59.3 | 63.2 | 34.7 | 50.9 | 53.2 | 36.9 | 29.1 | 57.7 | 48.8 | 39.3 | 66.7 | 48.1 | 33.8 |
), ArticleFig(id=1329381590850974663, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 7, caption=
Average Accuracy of Each Method over Office Under CDA and PDA %
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | Office (31/0/0) | | Office (10/21/0) |
|---|
| A2W | D2W | W2D | A2D | D2A | W2A | 平均 | A2W | D2W | W2D | A2D | D2A | W2A | 平均 |
|---|
| 是 | UAN[7] | 35.2 | 69.0 | 71.5 | 39.5 | 40.7 | 41.5 | 49.6 | | 43.7 | 50.9 | 48.2 | 67.8 | 47.9 | 16.5 | 45.8 |
| CMU[16] | 76.8 | 94.0 | 94.9 | 81.7 | 53.5 | 56.3 | 76.2 | 63.9 | 94.0 | 91.7 | 68.9 | 81.1 | 87.6 | 81.2 |
| I-UAN[17] | 39.9 | 72.6 | 77.3 | 43.5 | 42.3 | 42.2 | 53.0 | 66.2 | 91.1 | 94.6 | 71.2 | 85.6 | 84.9 | 82.3 |
| DANCE[24] | 90.3 | 98.6 | 100.0 | 91.0 | 69.7 | 69.5 | 86.5 | 76.2 | 92.5 | 97.1 | 78.3 | 91.0 | 92.7 | 88.0 |
| DCC[27] | 77.2 | 91.1 | 97.4 | 59.8 | 56.0 | 66.7 | 74.7 | 58.7 | 100.0 | 100.0 | 81.7 | 38.7 | 66.0 | 74.2 |
| OVANet[29] | 70.1 | 95.3 | 99.5 | 76.0 | 39.9 | 45.0 | 71.0 | 58.2 | 93.2 | 99.1 | 74.8 | 54.7 | 59.9 | 73.3 |
| 文献[13] (clean) | 87.0 | 98.3 | 99.8 | 88.4 | 56.0 | 59.8 | 81.5 | 84.7 | 77.9 | 88.6 | 79.2 | 59.3 | 87.8 | 79.6 |
| 否 | UB2DA[11](SF) | 76.3 | 93.5 | 99.7 | 85.0 | 53.0 | 55.1 | 77.1 | | 67.1 | 84.5 | 89.3 | 79.1 | 69.2 | 67.9 | 76.2 |
| UB2DA[11](BX) | 68.2 | 90.5 | 88.3 | 72.5 | 53.0 | 55.5 | 71.3 | 67.8 | 82.6 | 86.1 | 79.9 | 61.8 | 63.8 | 73.7 |
), ArticleFig(id=1329381590930666440, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表7, caption=
CDA和PDA情形下各方法在Office上的平均准确度
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | Office (31/0/0) | | Office (10/21/0) |
|---|
| A2W | D2W | W2D | A2D | D2A | W2A | 平均 | A2W | D2W | W2D | A2D | D2A | W2A | 平均 |
|---|
| 是 | UAN[7] | 35.2 | 69.0 | 71.5 | 39.5 | 40.7 | 41.5 | 49.6 | | 43.7 | 50.9 | 48.2 | 67.8 | 47.9 | 16.5 | 45.8 |
| CMU[16] | 76.8 | 94.0 | 94.9 | 81.7 | 53.5 | 56.3 | 76.2 | 63.9 | 94.0 | 91.7 | 68.9 | 81.1 | 87.6 | 81.2 |
| I-UAN[17] | 39.9 | 72.6 | 77.3 | 43.5 | 42.3 | 42.2 | 53.0 | 66.2 | 91.1 | 94.6 | 71.2 | 85.6 | 84.9 | 82.3 |
| DANCE[24] | 90.3 | 98.6 | 100.0 | 91.0 | 69.7 | 69.5 | 86.5 | 76.2 | 92.5 | 97.1 | 78.3 | 91.0 | 92.7 | 88.0 |
| DCC[27] | 77.2 | 91.1 | 97.4 | 59.8 | 56.0 | 66.7 | 74.7 | 58.7 | 100.0 | 100.0 | 81.7 | 38.7 | 66.0 | 74.2 |
| OVANet[29] | 70.1 | 95.3 | 99.5 | 76.0 | 39.9 | 45.0 | 71.0 | 58.2 | 93.2 | 99.1 | 74.8 | 54.7 | 59.9 | 73.3 |
| 文献[13] (clean) | 87.0 | 98.3 | 99.8 | 88.4 | 56.0 | 59.8 | 81.5 | 84.7 | 77.9 | 88.6 | 79.2 | 59.3 | 87.8 | 79.6 |
| 否 | UB2DA[11](SF) | 76.3 | 93.5 | 99.7 | 85.0 | 53.0 | 55.1 | 77.1 | | 67.1 | 84.5 | 89.3 | 79.1 | 69.2 | 67.9 | 76.2 |
| UB2DA[11](BX) | 68.2 | 90.5 | 88.3 | 72.5 | 53.0 | 55.5 | 71.3 | 67.8 | 82.6 | 86.1 | 79.9 | 61.8 | 63.8 | 73.7 |
), ArticleFig(id=1329381590997775305, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 8, caption=
Average Accuracy of Each Method over OfficeHome and VisDA Under ODA %
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (25/0/40) | VisDA (6/0/6) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 54.6 | 71.1 | 78.9 | 59.3 | 62.3 | 70.9 | 66.5 | 56.6 | 79.6 | 70.9 | 61.0 | 81.9 | 67.8 | 59.4 |
| CMU[16] | 34.0 | 56.4 | 69.2 | 32.2 | 42.6 | 51.3 | 57.8 | 34.4 | 57.9 | 57.7 | 44.9 | 66.3 | 50.4 | 32.6 |
| I-UAN[17] | 57.7 | 72.9 | 82.2 | 67.4 | 69.7 | 75.9 | 66.9 | 55.7 | 77.9 | 71.1 | 60.4 | 80.0 | 69.8 | 43.5 |
| DANCE[24] | 63.8 | 81.4 | 87.2 | 70.9 | 71.9 | 83.4 | 67.4 | 57.5 | 84.3 | 77.0 | 68.1 | 85.0 | 74.8 | 63.8 |
| DCC[27] | 49.1 | 69.2 | 80.8 | 53.3 | 63.2 | 67.7 | 61.7 | 43.8 | 78.1 | 66.0 | 46.0 | 74.9 | 62.8 | 41.3 |
| OVANet[29] | 47.5 | 68.4 | 81.9 | 50.3 | 60.6 | 70.9 | 47.3 | 41.1 | 74.2 | 66.2 | 49.7 | 79.1 | 61.4 | 47.0 |
| 文献[13] (clean) | 63.7 | 76.5 | 84.8 | 65.5 | 72.6 | 80.0 | 66.6 | 60.1 | 82.2 | 75.3 | 66.7 | 82.1 | 73.0 | 40.4 |
| 否 | UB2DA[11](SF) | 56.6 | 78.5 | 83.7 | 63.9 | 70.5 | 78.1 | 62.3 | 49.6 | 81.1 | 73.7 | 55.3 | 82.8 | 69.7 | 38.0 |
| UB2DA[11](BX) | 54.1 | 77.7 | 86.5 | 59.7 | 69.3 | 78.5 | 54.3 | 48.8 | 81.2 | 69.5 | 51.5 | 82.3 | 67.8 | 17.3 |
), ArticleFig(id=1329381591069078474, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表8, caption=
ODA情形下各方法在OfficeHome和VisDA上的平均准确度
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (25/0/40) | VisDA (6/0/6) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 54.6 | 71.1 | 78.9 | 59.3 | 62.3 | 70.9 | 66.5 | 56.6 | 79.6 | 70.9 | 61.0 | 81.9 | 67.8 | 59.4 |
| CMU[16] | 34.0 | 56.4 | 69.2 | 32.2 | 42.6 | 51.3 | 57.8 | 34.4 | 57.9 | 57.7 | 44.9 | 66.3 | 50.4 | 32.6 |
| I-UAN[17] | 57.7 | 72.9 | 82.2 | 67.4 | 69.7 | 75.9 | 66.9 | 55.7 | 77.9 | 71.1 | 60.4 | 80.0 | 69.8 | 43.5 |
| DANCE[24] | 63.8 | 81.4 | 87.2 | 70.9 | 71.9 | 83.4 | 67.4 | 57.5 | 84.3 | 77.0 | 68.1 | 85.0 | 74.8 | 63.8 |
| DCC[27] | 49.1 | 69.2 | 80.8 | 53.3 | 63.2 | 67.7 | 61.7 | 43.8 | 78.1 | 66.0 | 46.0 | 74.9 | 62.8 | 41.3 |
| OVANet[29] | 47.5 | 68.4 | 81.9 | 50.3 | 60.6 | 70.9 | 47.3 | 41.1 | 74.2 | 66.2 | 49.7 | 79.1 | 61.4 | 47.0 |
| 文献[13] (clean) | 63.7 | 76.5 | 84.8 | 65.5 | 72.6 | 80.0 | 66.6 | 60.1 | 82.2 | 75.3 | 66.7 | 82.1 | 73.0 | 40.4 |
| 否 | UB2DA[11](SF) | 56.6 | 78.5 | 83.7 | 63.9 | 70.5 | 78.1 | 62.3 | 49.6 | 81.1 | 73.7 | 55.3 | 82.8 | 69.7 | 38.0 |
| UB2DA[11](BX) | 54.1 | 77.7 | 86.5 | 59.7 | 69.3 | 78.5 | 54.3 | 48.8 | 81.2 | 69.5 | 51.5 | 82.3 | 67.8 | 17.3 |
), ArticleFig(id=1329381591140381643, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 9, caption=
H-score of Each Method over OfficeHome and VisDA Under ODA %
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (25/0/40) | VisDA (6/0/6) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 20.8 | 17.9 | 9.9 | 19.7 | 16.6 | 16.9 | 20.3 | 21.8 | 20.6 | 12.6 | 12.9 | 12.6 | 16.9 | 41.7 |
| CMU[16] | 42.2 | 55.7 | 60.0 | 39.5 | 45.9 | 54.1 | 61.2 | 42.1 | 63.1 | 64.3 | 53.8 | 66.0 | 54.0 | 27.9 |
| I-UAN[17] | 36.2 | 41.7 | 47.1 | 49.4 | 40.8 | 48.3 | 42.5 | 34.3 | 41.2 | 43.3 | 35.8 | 38.2 | 41.6 | 15.6 |
| DANCE[24] | 53.5 | 55.5 | 32.0 | 47.3 | 55.3 | 32.2 | 55.9 | 59.6 | 38.7 | 29.2 | 41.9 | 46.1 | 45.6 | 64.8 |
| DCC[27] | 59.1 | 73.4 | 74.3 | 52.7 | 63.9 | 70.4 | 61.3 | 54.7 | 76.4 | 65.5 | 58.1 | 75.1 | 65.4 | 9.0 |
| OVANet[29] | 58.4 | 65.9 | 69.6 | 61.3 | 64.9 | 67.9 | 58.2 | 53.3 | 69.1 | 68.5 | 58.2 | 67.0 | 63.5 | 62.1 |
| 文献[13] (clean) | 10.9 | 4.5 | 16.4 | 41.0 | 13.2 | 21.0 | 43.6 | 22.3 | 25.4 | 32.9 | 12.6 | 7.8 | 21.0 | 5.2 |
| 否 | UB2DA[11](SF) | 56.0 | 63.4 | 69.4 | 64.1 | 65.0 | 70.5 | 62.7 | 53.9 | 68.0 | 58.5 | 51.6 | 61.6 | 62.1 | 44.6 |
| UB2DA[11](BX) | 56.5 | 64.5 | 69.7 | 64.7 | 66.3 | 69.7 | 59.4 | 54.3 | 70.3 | 63.7 | 51.6 | 62.8 | 62.8 | 18.9 |
), ArticleFig(id=1329381591211684812, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表9, caption=
ODA情形下各方法在OfficeHome和VisDA上的H-score
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (25/0/40) | VisDA (6/0/6) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 20.8 | 17.9 | 9.9 | 19.7 | 16.6 | 16.9 | 20.3 | 21.8 | 20.6 | 12.6 | 12.9 | 12.6 | 16.9 | 41.7 |
| CMU[16] | 42.2 | 55.7 | 60.0 | 39.5 | 45.9 | 54.1 | 61.2 | 42.1 | 63.1 | 64.3 | 53.8 | 66.0 | 54.0 | 27.9 |
| I-UAN[17] | 36.2 | 41.7 | 47.1 | 49.4 | 40.8 | 48.3 | 42.5 | 34.3 | 41.2 | 43.3 | 35.8 | 38.2 | 41.6 | 15.6 |
| DANCE[24] | 53.5 | 55.5 | 32.0 | 47.3 | 55.3 | 32.2 | 55.9 | 59.6 | 38.7 | 29.2 | 41.9 | 46.1 | 45.6 | 64.8 |
| DCC[27] | 59.1 | 73.4 | 74.3 | 52.7 | 63.9 | 70.4 | 61.3 | 54.7 | 76.4 | 65.5 | 58.1 | 75.1 | 65.4 | 9.0 |
| OVANet[29] | 58.4 | 65.9 | 69.6 | 61.3 | 64.9 | 67.9 | 58.2 | 53.3 | 69.1 | 68.5 | 58.2 | 67.0 | 63.5 | 62.1 |
| 文献[13] (clean) | 10.9 | 4.5 | 16.4 | 41.0 | 13.2 | 21.0 | 43.6 | 22.3 | 25.4 | 32.9 | 12.6 | 7.8 | 21.0 | 5.2 |
| 否 | UB2DA[11](SF) | 56.0 | 63.4 | 69.4 | 64.1 | 65.0 | 70.5 | 62.7 | 53.9 | 68.0 | 58.5 | 51.6 | 61.6 | 62.1 | 44.6 |
| UB2DA[11](BX) | 56.5 | 64.5 | 69.7 | 64.7 | 66.3 | 69.7 | 59.4 | 54.3 | 70.3 | 63.7 | 51.6 | 62.8 | 62.8 | 18.9 |
), ArticleFig(id=1329381591320736717, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 10, caption=
Average Accuracy of Each Method over OfficeHome and VisDA Under OPDA %
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (10/5/50) | VisDA (6/3/3) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 61.6 | 79.1 | 88.0 | 70.5 | 73.2 | 79.7 | 74.7 | 59.3 | 86.7 | 76.2 | 60.4 | 80.6 | 74.2 | 46.1 |
| CMU[16] | 34.0 | 56.4 | 69.2 | 32.2 | 42.6 | 51.3 | 57.8 | 34.4 | 78.0 | 67.9 | 49.5 | 72.1 | 53.8 | 26.5 |
| I-UAN[17] | 59.6 | 82.7 | 90.6 | 81.5 | 78.0 | 88.8 | 81.1 | 59.8 | 89.3 | 82.3 | 59.2 | 83.9 | 78.1 | 62.8 |
| DANCE[24] | 66.8 | 86.0 | 91.4 | 82.9 | 79.8 | 90.2 | 84.0 | 67.8 | 91.3 | 82.4 | 68.7 | 87.5 | 81.6 | 70.5 |
| DCC[27] | 62.7 | 85.8 | 91.2 | 62.6 | 73.9 | 83.5 | 61.3 | 51.7 | 88.3 | 73.5 | 51.2 | 86.4 | 72.7 | 46.7 |
| OVANet[29] | 49.5 | 79.2 | 91.6 | 62.0 | 66.4 | 80.0 | 62.9 | 46.8 | 87.4 | 73.6 | 52.3 | 84.2 | 69.7 | 47.9 |
| 文献[13] (clean) | 58.6 | 80.6 | 87.8 | 77.5 | 74.7 | 86.0 | 76.9 | 62.0 | 87.6 | 81.4 | 58.7 | 81.2 | 76.1 | 63.9 |
| 否 | UB2DA[11](SF) | 61.3 | 85.4 | 94.1 | 77.2 | 76.4 | 87.1 | 76.2 | 54.7 | 92.2 | 78.4 | 61.1 | 87.8 | 77.7 | 27.2 |
| UB2DA[11](BX) | 56.4 | 88.0 | 94.5 | 70.4 | 77.6 | 91.6 | 70.3 | 56.0 | 92.7 | 81.0 | 59.9 | 89.1 | 77.3 | 22.0 |
), ArticleFig(id=1329381591396234190, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表10, caption=
OPDA情形下各方法在OfficeHome和VisDA上的平均准确度
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (10/5/50) | VisDA (6/3/3) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 61.6 | 79.1 | 88.0 | 70.5 | 73.2 | 79.7 | 74.7 | 59.3 | 86.7 | 76.2 | 60.4 | 80.6 | 74.2 | 46.1 |
| CMU[16] | 34.0 | 56.4 | 69.2 | 32.2 | 42.6 | 51.3 | 57.8 | 34.4 | 78.0 | 67.9 | 49.5 | 72.1 | 53.8 | 26.5 |
| I-UAN[17] | 59.6 | 82.7 | 90.6 | 81.5 | 78.0 | 88.8 | 81.1 | 59.8 | 89.3 | 82.3 | 59.2 | 83.9 | 78.1 | 62.8 |
| DANCE[24] | 66.8 | 86.0 | 91.4 | 82.9 | 79.8 | 90.2 | 84.0 | 67.8 | 91.3 | 82.4 | 68.7 | 87.5 | 81.6 | 70.5 |
| DCC[27] | 62.7 | 85.8 | 91.2 | 62.6 | 73.9 | 83.5 | 61.3 | 51.7 | 88.3 | 73.5 | 51.2 | 86.4 | 72.7 | 46.7 |
| OVANet[29] | 49.5 | 79.2 | 91.6 | 62.0 | 66.4 | 80.0 | 62.9 | 46.8 | 87.4 | 73.6 | 52.3 | 84.2 | 69.7 | 47.9 |
| 文献[13] (clean) | 58.6 | 80.6 | 87.8 | 77.5 | 74.7 | 86.0 | 76.9 | 62.0 | 87.6 | 81.4 | 58.7 | 81.2 | 76.1 | 63.9 |
| 否 | UB2DA[11](SF) | 61.3 | 85.4 | 94.1 | 77.2 | 76.4 | 87.1 | 76.2 | 54.7 | 92.2 | 78.4 | 61.1 | 87.8 | 77.7 | 27.2 |
| UB2DA[11](BX) | 56.4 | 88.0 | 94.5 | 70.4 | 77.6 | 91.6 | 70.3 | 56.0 | 92.7 | 81.0 | 59.9 | 89.1 | 77.3 | 22.0 |
), ArticleFig(id=1329381591471731663, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 11, caption=
H-score of Each Method over OfficeHome and VisDA Under OPDA %
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (10/5/50) | VisDA (6/3/3) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 14.7 | 13.3 | 15.0 | 18.8 | 11.5 | 15.0 | 12.1 | 9.5 | 16.9 | 15.0 | 7.4 | 8.5 | 13.1 | 13.7 |
| CMU[16] | 42.2 | 55.7 | 60.0 | 39.5 | 45.9 | 54.1 | 61.2 | 42.1 | 67.7 | 64.0 | 51.3 | 62.0 | 53.8 | 25.5 |
| I-UAN[17] | 23.9 | 19.4 | 27.2 | 31.5 | 24.5 | 30.2 | 27.4 | 24.4 | 27.5 | 29.9 | 22.8 | 21.4 | 25.9 | 19.8 |
| DANCE[24] | 40.6 | 41.3 | 34.5 | 43.5 | 27.5 | 36.2 | 54.4 | 49.7 | 41.5 | 26.7 | 42.5 | 52.1 | 40.9 | 4.0 |
| DCC[27] | 62.9 | 75.3 | 81.3 | 28.7 | 73.2 | 82.4 | 68.7 | 58.5 | 83.3 | 74.9 | 60.0 | 81.7 | 69.2 | 43.9 |
| OVANet[29] | 62.1 | 76.3 | 80.0 | 71.0 | 69.7 | 75.8 | 73.0 | 60.1 | 80.0 | 75.7 | 63.6 | 79.2 | 72.2 | 30.0 |
| 文献[13] (clean) | 5.3 | 3.2 | 8.5 | 26.8 | 7.8 | 13.5 | 25.5 | 11.6 | 19.5 | 9.7 | 9.0 | 4.2 | 12.1 | 18.7 |
| 否 | UB2DA[11](SF) | 63.1 | 66.0 | 74.5 | 71.9 | 63.8 | 72.3 | 70.8 | 58.3 | 73.3 | 68.1 | 63.3 | 68.6 | 67.8 | 31.0 |
| UB2DA[11](BX) | 61.6 | 68.3 | 77.3 | 72.9 | 68.8 | 76.7 | 70.7 | 60.8 | 75.5 | 72.6 | 63.0 | 71.0 | 69.9 | 25.5 |
), ArticleFig(id=1329381591547229136, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表11, caption=
OPDA情形下各方法在OfficeHome和VisDA上的H-score
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | OfficeHome (10/5/50) | VisDA (6/3/3) |
|---|
| A2C | A2P | A2R | C2A | C2P | C2R | P2A | P2C | P2R | R2A | R2C | R2P | 平均 |
|---|
| 是 | UAN[7] | 14.7 | 13.3 | 15.0 | 18.8 | 11.5 | 15.0 | 12.1 | 9.5 | 16.9 | 15.0 | 7.4 | 8.5 | 13.1 | 13.7 |
| CMU[16] | 42.2 | 55.7 | 60.0 | 39.5 | 45.9 | 54.1 | 61.2 | 42.1 | 67.7 | 64.0 | 51.3 | 62.0 | 53.8 | 25.5 |
| I-UAN[17] | 23.9 | 19.4 | 27.2 | 31.5 | 24.5 | 30.2 | 27.4 | 24.4 | 27.5 | 29.9 | 22.8 | 21.4 | 25.9 | 19.8 |
| DANCE[24] | 40.6 | 41.3 | 34.5 | 43.5 | 27.5 | 36.2 | 54.4 | 49.7 | 41.5 | 26.7 | 42.5 | 52.1 | 40.9 | 4.0 |
| DCC[27] | 62.9 | 75.3 | 81.3 | 28.7 | 73.2 | 82.4 | 68.7 | 58.5 | 83.3 | 74.9 | 60.0 | 81.7 | 69.2 | 43.9 |
| OVANet[29] | 62.1 | 76.3 | 80.0 | 71.0 | 69.7 | 75.8 | 73.0 | 60.1 | 80.0 | 75.7 | 63.6 | 79.2 | 72.2 | 30.0 |
| 文献[13] (clean) | 5.3 | 3.2 | 8.5 | 26.8 | 7.8 | 13.5 | 25.5 | 11.6 | 19.5 | 9.7 | 9.0 | 4.2 | 12.1 | 18.7 |
| 否 | UB2DA[11](SF) | 63.1 | 66.0 | 74.5 | 71.9 | 63.8 | 72.3 | 70.8 | 58.3 | 73.3 | 68.1 | 63.3 | 68.6 | 67.8 | 31.0 |
| UB2DA[11](BX) | 61.6 | 68.3 | 77.3 | 72.9 | 68.8 | 76.7 | 70.7 | 60.8 | 75.5 | 72.6 | 63.0 | 71.0 | 69.9 | 25.5 |
), ArticleFig(id=1329381591626920913, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 12, caption=
Average Accuracy of Each Method over Office Under ODA and OPDA %
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | Office (10/0/21) | | Office (10/10/11) |
|---|
| A2W | D2W | W2D | A2D | D2A | W2A | 平均 | A2W | D2W | W2D | A2D | D2A | W2A | 平均 |
|---|
| 是 | UAN[7] | 90.8 | 94.0 | 93.5 | 88.9 | 89.6 | 89.2 | 91.0 | | 81.6 | 93.7 | 94.1 | 79.1 | 84.1 | 83.3 | 86.0 |
| CMU[16] | 82.9 | 91.7 | 93.4 | 87.1 | 80.8 | 84.2 | 86.7 | 55.3 | 91.6 | 93.6 | 79.4 | 78.0 | 87.9 | 81.0 |
| I-UAN[17] | 51.6 | 50.0 | 49.8 | 51.9 | 41.4 | 49.8 | 49.1 | 91.0 | 96.7 | 98.4 | 91.2 | 91.7 | 91.6 | 93.4 |
| DANCE[24] | 94.9 | 96.5 | 96.5 | 95.7 | 90.9 | 91.4 | 94.3 | 92.1 | 97.8 | 98.3 | 90.0 | 91.8 | 91.1 | 93.5 |
| DCC[27] | 87.9 | 95.5 | 96.8 | 91.7 | 92.2 | 91.8 | 92.6 | 81.9 | 92.3 | 92.3 | 88.2 | 89.9 | 85.1 | 88.3 |
| OVANet[29] | 82.7 | 97.2 | 96.6 | 88.6 | 73.6 | 88.6 | 87.9 | 76.5 | 96.4 | 99.3 | 84.9 | 66.2 | 75.0 | 83.0 |
| 文献[13] (clean) | 84.5 | 89.3 | 91.0 | 89.9 | 85.6 | 85.2 | 87.6 | 89.1 | 95.6 | 97.7 | 91.5 | 89.3 | 88.7 | 92.0 |
| 否 | UB2DA[11](SF) | 87.0 | 96.3 | 96.4 | 92.8 | 91.5 | 90.3 | 92.4 | | 83.7 | 98.0 | 95.8 | 86.1 | 89.4 | 87.4 | 90.1 |
| UB2DA[11](BX) | 89.9 | 97.6 | 96.5 | 96.8 | 92.7 | 91.2 | 94.1 | 82.7 | 97.8 | 98.8 | 89.2 | 91.5 | 91.0 | 91.8 |
), ArticleFig(id=1329381591706612690, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表12, caption=
ODA和OPDA情形下各方法在Office上的平均准确度
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | Office (10/0/21) | | Office (10/10/11) |
|---|
| A2W | D2W | W2D | A2D | D2A | W2A | 平均 | A2W | D2W | W2D | A2D | D2A | W2A | 平均 |
|---|
| 是 | UAN[7] | 90.8 | 94.0 | 93.5 | 88.9 | 89.6 | 89.2 | 91.0 | | 81.6 | 93.7 | 94.1 | 79.1 | 84.1 | 83.3 | 86.0 |
| CMU[16] | 82.9 | 91.7 | 93.4 | 87.1 | 80.8 | 84.2 | 86.7 | 55.3 | 91.6 | 93.6 | 79.4 | 78.0 | 87.9 | 81.0 |
| I-UAN[17] | 51.6 | 50.0 | 49.8 | 51.9 | 41.4 | 49.8 | 49.1 | 91.0 | 96.7 | 98.4 | 91.2 | 91.7 | 91.6 | 93.4 |
| DANCE[24] | 94.9 | 96.5 | 96.5 | 95.7 | 90.9 | 91.4 | 94.3 | 92.1 | 97.8 | 98.3 | 90.0 | 91.8 | 91.1 | 93.5 |
| DCC[27] | 87.9 | 95.5 | 96.8 | 91.7 | 92.2 | 91.8 | 92.6 | 81.9 | 92.3 | 92.3 | 88.2 | 89.9 | 85.1 | 88.3 |
| OVANet[29] | 82.7 | 97.2 | 96.6 | 88.6 | 73.6 | 88.6 | 87.9 | 76.5 | 96.4 | 99.3 | 84.9 | 66.2 | 75.0 | 83.0 |
| 文献[13] (clean) | 84.5 | 89.3 | 91.0 | 89.9 | 85.6 | 85.2 | 87.6 | 89.1 | 95.6 | 97.7 | 91.5 | 89.3 | 88.7 | 92.0 |
| 否 | UB2DA[11](SF) | 87.0 | 96.3 | 96.4 | 92.8 | 91.5 | 90.3 | 92.4 | | 83.7 | 98.0 | 95.8 | 86.1 | 89.4 | 87.4 | 90.1 |
| UB2DA[11](BX) | 89.9 | 97.6 | 96.5 | 96.8 | 92.7 | 91.2 | 94.1 | 82.7 | 97.8 | 98.8 | 89.2 | 91.5 | 91.0 | 91.8 |
), ArticleFig(id=1329381591807275987, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 13, caption=
H-score of Each Method over Office Under ODA and OPDA %
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | Office (10/0/21) | | Office (10/10/11) |
|---|
| A2W | D2W | W2D | A2D | D2A | W2A | 平均 | A2W | D2W | W2D | A2D | D2A | W2A | 平均 |
|---|
| 是 | UAN[7] | 48.5 | 65.6 | 53.8 | 44.1 | 65.7 | 55.4 | 55.5 | | 38.8 | 67.3 | 61.5 | 33.1 | 70.4 | 56.4 | 54.6 |
| CMU[16] | 52.0 | 50.0 | 42.5 | 44.2 | 54.3 | 55.4 | 49.7 | 83.6 | 51.8 | 54.7 | 50.4 | 73.7 | 64.6 | 63.1 |
| I-UAN[17] | 35.5 | 28.2 | 19.2 | 32.6 | 27.7 | 31.9 | 29.2 | 83.8 | 86.7 | 90.3 | 89.4 | 85.8 | 84.0 | 86.7 |
| DANCE[24] | 67.7 | 78.1 | 75.8 | 72.7 | 72.8 | 67.9 | 72.5 | 70.8 | 91.4 | 89.6 | 77.9 | 79.0 | 71.7 | 80.1 |
| DCC[27] | 83.8 | 90.5 | 78.6 | 84.6 | 82.9 | 79.8 | 83.4 | 76.3 | 86.0 | 84.7 | 85.1 | 73.5 | 82.4 | 81.3 |
| OVANet[29] | 84.6 | 96.8 | 99.6 | 87.4 | 82.1 | 81.8 | 88.7 | 79.9 | 95.2 | 95.5 | 84.5 | 77.5 | 82.6 | 85.9 |
| 文献[13] (clean) | 14.7 | 8.1 | 2.3 | 3.5 | 10.5 | 10.0 | 8.2 | 49.4 | 74.1 | 85.2 | 73.4 | 51.0 | 40.5 | 62.3 |
| 否 | UB2DA[11](SF) | 77.5 | 80.5 | 75.5 | 69.3 | 87.7 | 83.7 | 79.1 | | 69.9 | 90.9 | 73.5 | 61.1 | 88.6 | 83.2 | 77.9 |
| UB2DA[11](BX) | 80.8 | 88.0 | 79.4 | 81.7 | 91.3 | 82.5 | 83.9 | 77.7 | 91.4 | 95.0 | 78.3 | 91.3 | 89.8 | 87.2 |
), ArticleFig(id=1329381591886967764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表13, caption=
ODA和OPDA情形下各方法在Office上的H-score
, figureFileSmall=null, figureFileBig=null, tableContent=
是否获得 源域数据 | 方法 | Office (10/0/21) | | Office (10/10/11) |
|---|
| A2W | D2W | W2D | A2D | D2A | W2A | 平均 | A2W | D2W | W2D | A2D | D2A | W2A | 平均 |
|---|
| 是 | UAN[7] | 48.5 | 65.6 | 53.8 | 44.1 | 65.7 | 55.4 | 55.5 | | 38.8 | 67.3 | 61.5 | 33.1 | 70.4 | 56.4 | 54.6 |
| CMU[16] | 52.0 | 50.0 | 42.5 | 44.2 | 54.3 | 55.4 | 49.7 | 83.6 | 51.8 | 54.7 | 50.4 | 73.7 | 64.6 | 63.1 |
| I-UAN[17] | 35.5 | 28.2 | 19.2 | 32.6 | 27.7 | 31.9 | 29.2 | 83.8 | 86.7 | 90.3 | 89.4 | 85.8 | 84.0 | 86.7 |
| DANCE[24] | 67.7 | 78.1 | 75.8 | 72.7 | 72.8 | 67.9 | 72.5 | 70.8 | 91.4 | 89.6 | 77.9 | 79.0 | 71.7 | 80.1 |
| DCC[27] | 83.8 | 90.5 | 78.6 | 84.6 | 82.9 | 79.8 | 83.4 | 76.3 | 86.0 | 84.7 | 85.1 | 73.5 | 82.4 | 81.3 |
| OVANet[29] | 84.6 | 96.8 | 99.6 | 87.4 | 82.1 | 81.8 | 88.7 | 79.9 | 95.2 | 95.5 | 84.5 | 77.5 | 82.6 | 85.9 |
| 文献[13] (clean) | 14.7 | 8.1 | 2.3 | 3.5 | 10.5 | 10.0 | 8.2 | 49.4 | 74.1 | 85.2 | 73.4 | 51.0 | 40.5 | 62.3 |
| 否 | UB2DA[11](SF) | 77.5 | 80.5 | 75.5 | 69.3 | 87.7 | 83.7 | 79.1 | | 69.9 | 90.9 | 73.5 | 61.1 | 88.6 | 83.2 | 77.9 |
| UB2DA[11](BX) | 80.8 | 88.0 | 79.4 | 81.7 | 91.3 | 82.5 | 83.9 | 77.7 | 91.4 | 95.0 | 78.3 | 91.3 | 89.8 | 87.2 |
), ArticleFig(id=1329381591966659541, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 14, caption=
Performance of Reference[13] Given Different Noise Settings Where Source is Art and Target is Clipart Under OPDA
, figureFileSmall=null, figureFileBig=null, tableContent=
| 噪声类型 | 噪声 比例 | 未知类准 确度/% | 平均准 确度/% | H-score /% | 运行时间/s |
|---|
| 无噪声 | 0.0 | 2.7 | 58.6 | 5.3 | 14223.7 |
| pairflip | 0.2 | 5.4 | 58.7 | 9.9 | 11096.7 |
| symmetric | 0.2 | 4.3 | 55.6 | 8.1 | 11161.9 |
| pairflip | 0.5 | 7.0 | 21.2 | 10.7 | 10675.9 |
| symmetric | 0.5 | 4.6 | 35.0 | 8.2 | 9598.3 |
), ArticleFig(id=1329381592025379798, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表14, caption=
源域为Art、目标域为Clipart的OPDA情形中文献[13]在不同噪声设置下的表现
, figureFileSmall=null, figureFileBig=null, tableContent=
| 噪声类型 | 噪声 比例 | 未知类准 确度/% | 平均准 确度/% | H-score /% | 运行时间/s |
|---|
| 无噪声 | 0.0 | 2.7 | 58.6 | 5.3 | 14223.7 |
| pairflip | 0.2 | 5.4 | 58.7 | 9.9 | 11096.7 |
| symmetric | 0.2 | 4.3 | 55.6 | 8.1 | 11161.9 |
| pairflip | 0.5 | 7.0 | 21.2 | 10.7 | 10675.9 |
| symmetric | 0.5 | 4.6 | 35.0 | 8.2 | 9598.3 |
), ArticleFig(id=1329381592096682967, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 15, caption=
UMAN Performance Under OPDA Given Two Source Domains Where Target Domain is Art
, figureFileSmall=null, figureFileBig=null, tableContent=
| 源域1 | 源域2 | 未知类准 确度/% | 平均准 确度/% | H-score /% | 运行时间/s |
|---|
| Clipart | Product | 5.0 | 79.3 | 9.4 | 19464.3 |
| Clipart | Real World | 4.3 | 78.8 | 8.2 | 20066.6 |
| Product | Real World | 7.0 | 78.0 | 12.9 | 35120.5 |
), ArticleFig(id=1329381592184763352, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表15, caption=
目标域为Art的双源域OPDA情形下UMAN的表现
, figureFileSmall=null, figureFileBig=null, tableContent=
| 源域1 | 源域2 | 未知类准 确度/% | 平均准 确度/% | H-score /% | 运行时间/s |
|---|
| Clipart | Product | 5.0 | 79.3 | 9.4 | 19464.3 |
| Clipart | Real World | 4.3 | 78.8 | 8.2 | 20066.6 |
| Product | Real World | 7.0 | 78.0 | 12.9 | 35120.5 |
), ArticleFig(id=1329381592277038041, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 16, caption=
UMAN Performance Under OPDA Given Two Source Domains Where Target Domain is Clipart
, figureFileSmall=null, figureFileBig=null, tableContent=
| 源域1 | 源域2 | 未知类准 确度/% | 平均准 确度/% | H-score /% | 运行时间/s |
|---|
| Art | Product | 12.0 | 53.3 | 19.8 | 38392.6 |
| Art | Real World | 10.9 | 55.6 | 18.5 | 37343.9 |
| Product | Real World | 9.1 | 57.8 | 15.8 | 37790.3 |
), ArticleFig(id=1329381592344146907, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表16, caption=
目标域为Clipart的双源域OPDA下UMAN的表现
, figureFileSmall=null, figureFileBig=null, tableContent=
| 源域1 | 源域2 | 未知类准 确度/% | 平均准 确度/% | H-score /% | 运行时间/s |
|---|
| Art | Product | 12.0 | 53.3 | 19.8 | 38392.6 |
| Art | Real World | 10.9 | 55.6 | 18.5 | 37343.9 |
| Product | Real World | 9.1 | 57.8 | 15.8 | 37790.3 |
), ArticleFig(id=1329381592478364636, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=EN, label=Table 17, caption=
UMAN Performance Under OPDA Given Three Source Domains
, figureFileSmall=null, figureFileBig=null, tableContent=
| 目标域 | 未知类准 确度/% | 平均准 确度/% | H-score /% | 运行时间/s |
|---|
| Art | 2.0 | 66.3 | 4.0 | 43827.7 |
| Clipart | 12.2 | 57.4 | 20.4 | 42326.0 |
| Product | 4.2 | 71.9 | 8.0 | 39603.2 |
| Real World | 3.2 | 78.9 | 6.1 | 33204.4 |
), ArticleFig(id=1329381592562250717, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329381583255090021, language=CN, label=表17, caption=
3源域OPDA情形下UMAN的表现
, figureFileSmall=null, figureFileBig=null, tableContent=
| 目标域 | 未知类准 确度/% | 平均准 确度/% | H-score /% | 运行时间/s |
|---|
| Art | 2.0 | 66.3 | 4.0 | 43827.7 |
| Clipart | 12.2 | 57.4 | 20.4 | 42326.0 |
| Product | 4.2 | 71.9 | 8.0 | 39603.2 |
| Real World | 3.2 | 78.9 | 6.1 | 33204.4 |
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202220935, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202220935, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202220935, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202220935, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1704124800000, fullTextJson=null, articleText=null, reference=null)