Article(id=1329457012410265768, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329456888623771822, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202330085, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1676476800000, receivedDateStr=2023-02-16, revisedDate=1697040000000, revisedDateStr=2023-10-12, acceptedDate=null, acceptedDateStr=null, onlineDate=1794896851875, onlineDateStr=2026-11-17, pubDate=1719763200000, pubDateStr=2024-07-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794896851875, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794896851875, creator=13701087609, updateTime=1794896851875, updator=13701087609, issue=Issue{id=1329456888623771822, tenantId=1146029695717560320, journalId=1324759914146529478, year='2024', volume='61', issue='7', pageStart='1609', pageEnd='1862', issueExtLink='null', onlineDate='null', pubDate='1719763200000', pubDateStr='2024-07-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794896822361, creator='13701087609', updateTime=1794896822361, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=1836, endPage=1849, ext={EN=ArticleExt(id=1329457014167679145, articleId=1329457012410265768, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Feature-Oriented and Decoupled Network Structure Based Filter Pruning Method, columnId=1325489891789910943, journalTitle=Journal of Computer Research and Development, columnName=Artificial Intelligence, runingTitle=null, highlight=null, articleAbstract=
Many existing pruning methods for deep neural network models require modifying the loss function or embedding additional variables in the network, thus they can’t benefit from the pre-trained network directly, and complicate the forward inference and training process. So far, most of the feature-oriented pruning work only use the intra-channel information to analyze the importance of filters, which makes it impossible to use the potential connections among channels during the pruning process. To address these issues, we consider the feature-oriented filter pruning task from an inter-channel perspective. The proposed method uses geometric distance to measure the potential correlation among channels, defines filter pruning as an optimization problem, and applies a greedy strategy to find an approximate solution to the optimal solution. The method achieves the decoupling of pruning from network and pruning from training, thus simplifying the pruning task. Extensive experiments demonstrate that the proposed pruning method achieves high performance for various network structures, for example, on CIFAR-10 dataset, the number of parameters and floating point operations of VGG-16 are reduced by 87.1% and 63.7%, respectively, while still has an accuracy of 93.81%. We also evaluate the proposed method using MobileFaceNets, a lightweight network, on CASIA-WebFace large dataset, and the evaluation results show that, when the number of parameters and floating-point operations are reduced by 58.0% and 63.6%, respectively, MobileFaceNets achieves an accuracy of 99.02% on LFW dataset without loss of inference accuracy (The code is available at: https://github.com/SSriven/FOAD).
, authors=Ruiwen Shi
1, Guanghui Li
1, Chenglong Dai
1, Feifei Zhang
2, authorsList=Ruiwen Shi, Guanghui Li, Chenglong Dai, Feifei Zhang, authorCompany=null, correspAuthors=null, authorNote=
born in 1999. Master. His main research interests include model compression and deep learning
born in 1970. PhD, professor and PhD supervisor. Senior member of CCF. His main research interests include wireless sensor network, model compression and intelligent nondestructive detection technology
born in 1992. Lecturer. His main research interests include electroencephalogram processing, electroencephalogram analyzing, and model compression
born in 1982. Master. His main research interests include the hardware acceleration implementation of image processing algorithm and SoC chip design
, 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=1329457015912509626, articleId=1329457012410265768, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=一种基于特征导向解耦网络结构的滤波器修剪方法, columnId=1325489892104483745, journalTitle=计算机研究与发展, columnName=人工智能, runingTitle=null, highlight=null, articleAbstract=
现有的很多深度神经网络模型剪枝方法需要修改损失函数或在网络中嵌入额外的变量,无法直接受益于预训练网络,而且复杂化了前向推理和训练过程. 到目前为止,大部分特征导向的剪枝工作仅利用通道内信息分析滤波器的重要性,使得剪枝过程无法利用通道间的潜在联系. 针对上述问题,基于特征导向从通道间的角度考虑滤波器修剪任务,使用几何距离度量通道间的潜在相关性,将滤波器修剪定义为一个优化问题,并引入贪婪策略寻求最优解的近似解. 该方法实现了剪枝与网络、剪枝与训练的解耦,从而简化了修剪任务. 大量的实验证明了该方法对于各种网络结构都有良好的性能,例如在CIFAR-10数据集上,将VGG-16的参数量和浮点运算量分别降低了87.1%和63.7%,并且达到93.81%的高精度. 还使用轻量型网络MobileFaceNets和CASIA-WebFace数据集评估该方法的性能,结果显示使用该剪枝方法后,MobileFaceNets在参数量和浮点运算量分别降低58.0%和63.6%的情况下,在LFW上的测试精度仍然达到99.02%,而且推理精度几乎没有损失(源代码发布在:https://github.com/SSriven/FOAD).
, authors=施瑞文
1, 李光辉
1, 代成龙
1, 张飞飞
2, authorsList=施瑞文, 李光辉, 代成龙, 张飞飞, authorCompany=null, correspAuthors=null, authorNote=
 |
1999年生. 硕士. 主要研究方向为模型压缩、深度学习 |
 |
1970年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为无线传感网、模型压缩、智能无损检测技术 |
 |
1992年生. 讲师. 主要研究方向为脑电图处理、脑电图分析、模型压缩 |
 |
1982年生. 硕士. 主要研究方向为图像处理算法的硬件加速、SoC芯片设计 |
, correspAuthorsNote=null, copyrightStatement=版权所有 © 2024 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=qvCPU+xVP55jVZoKWA47gA==, magXml=wIlz5/zaXkW1yq52i0Lscw==, pdfUrl=null, pdf=BxsSe2vECh5gFZzWNajAbQ==, pdfFileSize=1596356, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=UFN/VawIIk96TP5SCbgf2w==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=xI3SaPIwWxvBvARGG9ApAw==, mapNumber=null, fund=null)}, authors=[Author(id=1329457016348717250, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=srw0109@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329457016424214724, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, authorId=1329457016348717250, language=EN, stringName=Ruiwen Shi, firstName=Ruiwen, middleName=null, lastName=Shi, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122, bio={"content":"
born in 1999. Master. His main research interests include model compression and deep learning
"}, bioImg=null, bioContent=
born in 1999. Master. His main research interests include model compression and deep learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329457016487129285, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, authorId=1329457016348717250, language=CN, stringName=施瑞文, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1江南大学人工智能与计算机学院 江苏无锡 214122, bio={"img":"d7+6XOSm3VHbOHh3IeZsqA==","content":"
1999年生. 硕士. 主要研究方向为模型压缩、深度学习
"}, bioImg=d7+6XOSm3VHbOHh3IeZsqA==, bioContent=
1999年生. 硕士. 主要研究方向为模型压缩、深度学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329457016180945083, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, xref=1, ext=[AuthorCompanyExt(id=1329457016189333692, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016180945083, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122), AuthorCompanyExt(id=1329457016201916605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016180945083, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1江南大学人工智能与计算机学院 江苏无锡 214122)])]), Author(id=1329457016545849543, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329457016629735625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, authorId=1329457016545849543, language=EN, stringName=Guanghui Li, firstName=Guanghui, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122, bio={"content":"
born in 1970. PhD, professor and PhD supervisor. Senior member of CCF. His main research interests include wireless sensor network, model compression and intelligent nondestructive detection technology
"}, bioImg=null, bioContent=
born in 1970. PhD, professor and PhD supervisor. Senior member of CCF. His main research interests include wireless sensor network, model compression and intelligent nondestructive detection technology
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329457016688455882, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, authorId=1329457016545849543, language=CN, stringName=李光辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1江南大学人工智能与计算机学院 江苏无锡 214122, bio={"img":"qQkJprzX34qxi7V20I5dHg==","content":"
1970年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为无线传感网、模型压缩、智能无损检测技术
"}, bioImg=qQkJprzX34qxi7V20I5dHg==, bioContent=
1970年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为无线传感网、模型压缩、智能无损检测技术
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329457016180945083, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, xref=1, ext=[AuthorCompanyExt(id=1329457016189333692, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016180945083, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122), AuthorCompanyExt(id=1329457016201916605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016180945083, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1江南大学人工智能与计算机学院 江苏无锡 214122)])]), Author(id=1329457016759759052, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329457016831062222, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, authorId=1329457016759759052, language=EN, stringName=Chenglong Dai, firstName=Chenglong, middleName=null, lastName=Dai, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122, bio={"content":"
born in 1992. Lecturer. His main research interests include electroencephalogram processing, electroencephalogram analyzing, and model compression
"}, bioImg=null, bioContent=
born in 1992. Lecturer. His main research interests include electroencephalogram processing, electroencephalogram analyzing, and model compression
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329457016910753999, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, authorId=1329457016759759052, language=CN, stringName=代成龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1江南大学人工智能与计算机学院 江苏无锡 214122, bio={"img":"b24ImRmjTvlQISH3RujFXQ==","content":"
1992年生. 讲师. 主要研究方向为脑电图处理、脑电图分析、模型压缩
"}, bioImg=b24ImRmjTvlQISH3RujFXQ==, bioContent=
1992年生. 讲师. 主要研究方向为脑电图处理、脑电图分析、模型压缩
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329457016180945083, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, xref=1, ext=[AuthorCompanyExt(id=1329457016189333692, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016180945083, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122), AuthorCompanyExt(id=1329457016201916605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016180945083, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1江南大学人工智能与计算机学院 江苏无锡 214122)])]), Author(id=1329457018517172433, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329457018643001556, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, authorId=1329457018517172433, language=EN, stringName=Feifei Zhang, firstName=Feifei, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2Jiangsu Bangrong Microelectronics Co., Ltd., Kunshan, Jiangsu 215300, bio={"content":"
born in 1982. Master. His main research interests include the hardware acceleration implementation of image processing algorithm and SoC chip design
"}, bioImg=null, bioContent=
born in 1982. Master. His main research interests include the hardware acceleration implementation of image processing algorithm and SoC chip design
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329457018752053461, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, authorId=1329457018517172433, language=CN, stringName=张飞飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2江苏邦融微电子有限公司 江苏昆山 215300, bio={"img":"a/8hTpjpLrhGIUTI2z10hA==","content":"
1982年生. 硕士. 主要研究方向为图像处理算法的硬件加速、SoC芯片设计
"}, bioImg=a/8hTpjpLrhGIUTI2z10hA==, bioContent=
1982年生. 硕士. 主要研究方向为图像处理算法的硬件加速、SoC芯片设计
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329457016281608382, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, xref=2, ext=[AuthorCompanyExt(id=1329457016289996991, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016281608382, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Jiangsu Bangrong Microelectronics Co., Ltd., Kunshan, Jiangsu 215300), AuthorCompanyExt(id=1329457016298385600, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016281608382, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2江苏邦融微电子有限公司 江苏昆山 215300)])])], keywords=[Keyword(id=1329457018873688278, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, orderNo=1, keyword=deep learning), Keyword(id=1329457018986934487, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, orderNo=2, keyword=model compression), Keyword(id=1329457019054043352, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, orderNo=3, keyword=model pruning), Keyword(id=1329457019108569305, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, orderNo=4, keyword=neural network acceleration), Keyword(id=1329457021042143450, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, orderNo=5, keyword=geometric distance), Keyword(id=1329457021113446619, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, orderNo=1, keyword=深度学习), Keyword(id=1329457021214109916, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, orderNo=2, keyword=模型压缩), Keyword(id=1329457021318967517, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, orderNo=3, keyword=模型剪枝), Keyword(id=1329457021394464990, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, orderNo=4, keyword=神经网络加速), Keyword(id=1329457023047020768, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, orderNo=5, keyword=几何距离)], refs=[Reference(id=1329457024754102515, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, 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=Pohlen T, Hermans A, Mathias M, et al. Full-Resolution residual networks for semantic segmentation in street scenes [C] // Proc of the 2017 IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 3309−3318, articleTitle=null, refAbstract=null), Reference(id=1329457024825405684, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, 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=Dettmers T. 8-bit approximations for parallelism in deep learning[J]. arXiv preprint, arXiv: 1511.04561, 2016, articleTitle=null, refAbstract=null), Reference(id=1329457028306678005, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Hwang K, Sung W. Fixed-point feedforward deep neural network design using weights +1, 0, and −1[C] // Proc of the 2014 IEEE Workshop on Signal Processing Systems. Piscataway, NJ: IEEE, 2014: 174−179, articleTitle=null, refAbstract=null), Reference(id=1329457028440895734, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Courbariaux M, Bengio Y, David J. BinaryConnect: Training deep neural networks with binary weights during propagations [C] // Proc of the Annual Conf on Neural Information Processing Systems 2015. Piscataway, NJ: IEEE 2015: 3123−3131, articleTitle=null, refAbstract=null), Reference(id=1329457028541559031, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Courbariaux M, Bengio Y. BinaryNet: Training deep neural networks with weights and activations constrained to +1 or -1 [J]. arXiv preprint, arXiv: 1602.02830, 2016, articleTitle=null, refAbstract=null), Reference(id=1329457028600279288, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Rastegari M, Ordonez V, Redmon J, et al. XNOR-Net: ImageNet classification using binary convolutional neural networks [C] // Proc of the 14th European Conf on Computer Vision. Berlin: Springer, 2016: 525−542, articleTitle=null, refAbstract=null), Reference(id=1329457028671582457, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=龚成,卢冶,代素蓉,等. 一种超低损失的深度神经网络量化压缩方法[J]. 软件学报,2021,32(8):2391−2407, articleTitle=null, refAbstract=null), Reference(id=1329457028751274234, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, 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=Gong Cheng, Lu Ye, Dai Surong, et al. Ultra-low loss quantization method for deep neural network compression[J]. Journal of Software, 2021, 32(8): 2391−2407 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329457028843548923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, 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=Romero A, Ballas N, Kahou S, et al. FitNets: Hints for thin deep nets[J]. arXiv preprint, arXiv: 1412.6550, 2015, articleTitle=null, refAbstract=null), Reference(id=1329457028898074876, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, 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=Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network[J]. arXiv preprint, arXiv: 1503.02531, 2015, articleTitle=null, refAbstract=null), Reference(id=1329457028956795133, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, 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=张晶,王子铭,任永功. A3C深度强化学习模型压缩及知识抽取[J]. 计算机研究与发展,2023,60(6):1373−1384, articleTitle=null, refAbstract=null), Reference(id=1329457029049069823, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Jing, Wang Ziming, Ren Yonggong. A3C deep reinforcement learning model compression and knowledge extraction[J]. Journal of Computer Research and Development, 2023, 60(6): 1373−1384 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329457029124567296, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=林振元,林绍辉,姚益武,等. 多教师对比知识反演的无数据模型压缩方法[J/OL]. 计算机科学与探索,2022[2023-09-13]. http://fcst.ceaj.org/CN/10.3778/j.issn.1673-9418.2204107, articleTitle=null, refAbstract=null), Reference(id=1329457029195870465, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Zhenyuan, Lin Shaohui, Yao Yiwu, et al. Multi-teacher contrastive knowledge inversion for data-free distillation[J/OL]. Journal of Frontiers of Computer Science and Technology, 2022[2023-09-13]. http://fcst.ceaj.org/CN/10.3778/j.issn.1673-9418.2204107 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329457029262979330, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Han Song, Mao Huizi, William J, et al. Deep compression: Compressing deep neural network with pruning, trained quantization and Huffman coding[J]. arXiv preprint, arXiv: 1510.00149, 2016, articleTitle=null, refAbstract=null), Reference(id=1329457029325893891, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Hao, Kadav A, Durdanovic I, et al. Pruning filters for efficient ConvNets [C/OL] // Proc of the 5th Int Conf on Learning Representations. Berlin: Springer, 2017[2023-09-13]. https://openreview.net/forum?id=rJqFGTslg, articleTitle=null, refAbstract=null), Reference(id=1329457029384614148, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Tao, U. Stich S , Barba L, et al. Dynamic model pruning with feedback [C/OL] // Proc of the 8th Int Conf on Learning Representations. Berlin: Springer, 2020[2023-09-13]. https://openreview.net/forum?id=SJem8lSFwB, articleTitle=null, refAbstract=null), Reference(id=1329457029443334405, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu M, Gupta S. To prune, or not to prune: Exploring the efficacy of pruning for model compression [C/OL] // Proc of the 6th Int Conf on Learning Representations. Berlin: Springer, 2018[2023-09-13]. https://openreview.net/forum?id=Sy1iIDkPM, articleTitle=null, refAbstract=null), Reference(id=1329457029510443270, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Frankle J, Carbin M. The lottery ticket hypothesis: Finding sparse, trainable neural networks [C/OL]// Proc of the 7th Int Conf on Learning Representations. Berlin: Springer, 2019[2023-09-13]. https://openreview.net/forum?id=rJl-b3RcF7, articleTitle=null, refAbstract=null), Reference(id=1329457029594329351, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Guo Yiwen, Yao Anbang, Chen Yurong. Dynamic network surgery for efficient DNNs [C]// Proc of the Annual Conf on Neural Information Processing Systems 2016. Piscataway, NJ: IEEE, 2016: 1379−1387, articleTitle=null, refAbstract=null), Reference(id=1329457029661438216, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Han Song, Liu Xingyu, Mao Huizi, et al. EIE: Efficient inference engine on compressed deep neural network [C] // Proc of the 43rd ACM/IEEE Annual Int Symp on Computer Architecture. Piscataway, NJ: IEEE, 2016: 243−254, articleTitle=null, refAbstract=null), Reference(id=1329457029728547081, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=He Yang, Kang Guoliang, Dong Xuanyi, et al. Soft filter pruning for accelerating deep convolutional neural networks [C] // Proc of the 27th Int Joint Conf on Artificial Intelligence. Berlin: Springer, 2018: 2234−2240, articleTitle=null, refAbstract=null), Reference(id=1329457029795655946, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Zhuang, Li Jianguo, Shen Zhiqiang, et al. Learning efficient convolutional networks through network slimming [C]// Proc of the IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2017: 2755−2763, articleTitle=null, refAbstract=null), Reference(id=1329457029866959115, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Meng Fanxu, Cheng Hao, Li Ke, et al. Pruning filter in filter [C/OL] // Proc of the Annual Conf on Neural Information Processing Systems 2020. Piscataway, NJ: IEEE, 2020[2023-09-13]. https://proceedings.neurips.cc/paper/2020/hash/ccb1d45fb76f7c5a0bf619f979c6cf36-Abstract.html, articleTitle=null, refAbstract=null), Reference(id=1329457029929873676, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Mingbao, Ji Rongrong, Wang Yan, et al. HRank: Filter pruning using high-rank feature map [C] // Proc of the 2020 IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 1526−1535, articleTitle=null, refAbstract=null), Reference(id=1329457030026342669, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang Yehui, Wang Yunhe, Xu Yixing, et al. SCOP: Scientific control for reliable neural network pruning [C/OL] // Proc of the Annual Conf on Neural Information Processing Systems 2020. Piscataway, NJ: IEEE, 2020[2023-09-13]. https://proceedings.neurips.cc/paper/2020/hash/7bcdf75ad237b8e02e301f4091fb6bc8-Abstract.html, articleTitle=null, refAbstract=null), Reference(id=1329457030080868622, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Suau X, Zappella L, Apostoloff N, et al. Network compression using correlation analysis of layer responses [C/OL] // Proc of the 2018 IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018[2023-09-13]. https://readpaper.com/pdf-annotate/note?noteId=1959569544894668800, articleTitle=null, refAbstract=null), Reference(id=1329457030257029391, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Sui Yang, Yin Miao, Xie Yi, et al. CHIP: Channel independence-based pruning for compact neural networks [C] // Proc of the Annual Conf on Neural Information Processing Systems 2021. Piscataway, NJ: IEEE , 2021: 24604−24616, articleTitle=null, refAbstract=null), Reference(id=1329457030319943952, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Di, Cao Yuan, Yang Qiang. On the channel pruning using graph convolution network for convolutional neural network acceleration[C] // Proc of the 21st Int Joint Conf on Artificial Intelligence. Berlin: Springer, 2022: 3107−3113, articleTitle=null, refAbstract=null), Reference(id=1329457031917973779, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhuang Tao, Zhang Zhixuan, Huang Yuheng, et al. Neuron-level structured pruning using polarization regularizer [C/OL] // Proc of the Annual Conf on Neural Information Processing Systems 2020. Piscataway, NJ: IEEE, 2020[2023-09-13]. https://proceedings.neurips.cc/paper/2020/hash/703957b6dd9e3a7980e040bee50ded65-Abstract.html, articleTitle=null, refAbstract=null), Reference(id=1329457031985082644, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=You Zhonghui, Yan Kun, Ye Jinmian , et al. Gate Decorator: Global filter pruning method for accelerating deep convolutional neural networks [C] // Proc of the Annual Conf on Neural Information Processing Systems 2019. Piscataway, NJ: IEEE, 2019: 2130−2141, articleTitle=null, refAbstract=null), Reference(id=1329457032043802901, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=He Yang , Liu Ping , Wang Ziwei , et al. Filter pruning via geometric median for deep convolutional neural networks acceleration [C] // Proc of the Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 4340−4349, articleTitle=null, refAbstract=null), Reference(id=1329457032110911766, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Dubey A, Moitreya C, Ahuja N, et al. Coreset-based neural network compression [C] // Proc of the 15th European Conf Computer Vision. Piscataway, NJ: IEEE, 2018: 469−486, articleTitle=null, refAbstract=null), Reference(id=1329457032165437719, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Wenxiao, Cong Fu, Guo Jishun, et al. COP: Customized deep model compression via regularized correlation-based filter-level pruning [C] // Proc of the 28th Int Joint Conf on Artificial Intelligence. Berlin: Springer, 2019: 3785−3791, articleTitle=null, refAbstract=null), Reference(id=1329457032236740888, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Luo Jianhao, Wu Jianxin, Lin Weiyao, et al. ThiNet: A filter level pruning method for deep neural network compression [C] // Proc of the IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2017: 5068−5076, articleTitle=null, refAbstract=null), Reference(id=1329457032299655449, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=He Yihui, Zhang Xiangyu, Sun Jian. Channel pruning for accelerating very deep neural networks [C] // Proc of the IEEE Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2017: 1398−1406, articleTitle=null, refAbstract=null), Reference(id=1329457032362570010, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhuang Zhuangwei, Tan Mingkui, Zhuang Bohan, et al. Discrimination-aware channel pruning for deep neural networks [C] // Proc of the Annual Conf on Neural Information Processing Systems 2018. Piscataway, NJ: IEEE, 2018: 883−894, articleTitle=null, refAbstract=null), Reference(id=1329457032425484571, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yawei, Gu Shuhang, Mayer C, et al. Group sparsity: The hinge between filter pruning and decomposition for network compression [C] // Proc of the 2020 IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 8015−8024, articleTitle=null, refAbstract=null), Reference(id=1329457032492593436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Tiwari R, Bamba U, Chavan A, et al. ChipNet: Budget-aware pruning with heaviside continuous approximations [C/OL] // Proc of the 9th Int Conf on Learning Representations. Berlin: Springer, 2021[2023-09-13]. https://openreview.net/forum?id=xCxXwTzx4L1, articleTitle=null, refAbstract=null), Reference(id=1329457032576479517, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Tianyi, Ji Bo, Ding Tianyu, et al. Only train once: A one-shot neural network training and pruning framework [C] // Proc of the Annual Conf on Neural Information Processing Systems 2021. Piscataway, NJ: IEEE, 2021: 19637−19651, articleTitle=null, refAbstract=null), Reference(id=1329457032639394078, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Mingbao, Ji Rongrong, Zhang Yuxin, et al. Channel pruning via automatic structure search [C] // Proc of the 29th Int Joint Conf on Artificial Intelligence. Berlin: Springer, 2020: 673−679, articleTitle=null, refAbstract=null), Reference(id=1329457032698114335, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Dong Xuanyi, Yang Yi. Network pruning via transformable architecture search [C] // Proc of the Annual Conf on Neural Information Processing Systems 2019. Piscataway, NJ: IEEE, 2019: 759−770, articleTitle=null, refAbstract=null), Reference(id=1329457032769417504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Edouard Y, Arnaud D, Matthieu C, et al. RED : Looking for redundancies for data-free structured compression of deep neural networks[J]. arXiv preprint, arXiv: 2105.14797, 2021, articleTitle=null, refAbstract=null), Reference(id=1329457032857497889, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Shiwei, Chen Tianlong, Chen Xiaohan, et al. Sparse training via boosting pruning plasticity with neuroregeneration [C] // Proc of the Annual Conf on Neural Information Processing Systems 2021. Piscataway, NJ: IEEE, 2021: 9908−9922, articleTitle=null, refAbstract=null), Reference(id=1329457032924606754, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images[J/OL]. Handbook of Systemic Autoimmune Diseases, 2009[2023-09-13]. https://xueshu.baidu.com/usercenter/paper/show?paperid=c55665fb879e98e130fce77052d4c8e8&site=xueshu_se, articleTitle=null, refAbstract=null), Reference(id=1329457032995909923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Sheng, Liu Yang, Gao Xiang, et al. MobileFaceNets: Efficient CNNs for accurate real-time face verification on mobile devices [C] // Proc of the 13th Chinese Conf on Biometric Recognition. Berlin: Springer, 2018: 428−438, articleTitle=null, refAbstract=null), Reference(id=1329457033050435876, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang G, Mattar M, Berg T, et al. Labeled faces in the wild: A database for studying face recognition in unconstrained environments [C/OL] // Proc of the Workshop on Faces in 'Real-Life' Images: Detection, Alignment, and Recognition. 2008[2023-09-13]. https://cs.brown.edu/courses/csci1430/2011/proj4/papers/lfw.pdf, articleTitle=null, refAbstract=null), Reference(id=1329457033113350437, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Zehao, Wang Naiyan. Data-driven sparse structure selection for deep neural networks [C] // Proc of the 15th European Conf on Computer Vision. Piscataway, NJ: IEEE, 2018: 317−334, articleTitle=null, refAbstract=null), Reference(id=1329457033184653606, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Shaohui, Ji Rongrong, Yan Chenqian, et al. Towards optimal structured CNN pruning via generative adversarial learning [C] // Proc of the IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 2790−2799, articleTitle=null, refAbstract=null), Reference(id=1329457033247568167, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Ruichi, Li Ang, Chen Chunfu, et al. NISP: Pruning networks using neuron importance score propagation [C] // Proc of the 2018 IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 9194–9203, articleTitle=null, refAbstract=null), Reference(id=1329457033323065640, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Mingbao, Cao Liujuan, Li Shaojie, et al. Filter sketch for network pruning[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(12): 7091−7100, articleTitle=null, refAbstract=null), Reference(id=1329457033377591593, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Fernandes F, Yen G. Pruning deep convolutional neural net-works architectures with evolution strategy [C/OL] // Proc of the Information Sciences. Amsterdam: Elsevier, 2021[2023-09-13].https://doi.org/10.1016/j.ins.2020.11.009, articleTitle=null, refAbstract=null), Reference(id=1329457033440506154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Linhang, An Zhulin, Yang Chuanguang, et al. Prior gradient mask guided pruning-aware fine-tuning [C/OL] // Proc of the AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2022[2023-09-13]. http://dx. doi.org/10.1609/aaai.v36i1.19888, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329457016180945083, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, xref=1, ext=[AuthorCompanyExt(id=1329457016189333692, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016180945083, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, Jiangsu 214122), AuthorCompanyExt(id=1329457016201916605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016180945083, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1江南大学人工智能与计算机学院 江苏无锡 214122)]), AuthorCompany(id=1329457016281608382, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, xref=2, ext=[AuthorCompanyExt(id=1329457016289996991, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016281608382, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Jiangsu Bangrong Microelectronics Co., Ltd., Kunshan, Jiangsu 215300), AuthorCompanyExt(id=1329457016298385600, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, companyId=1329457016281608382, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2江苏邦融微电子有限公司 江苏昆山 215300)])], figs=[ArticleFig(id=1329457023177044193, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, label=Figure 1, caption=
Greedy pruning of the filter based on the geometric distance between feature channels, figureFileSmall=KCscOMPhv5fSPhcHPFhK5Q==, figureFileBig=UFN/VawIIk96TP5SCbgf2w==, tableContent=null), ArticleFig(id=1329457023239958754, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, label=图1, caption=
根据特征通道间的几何距离贪婪地修剪滤波器, figureFileSmall=KCscOMPhv5fSPhcHPFhK5Q==, figureFileBig=UFN/VawIIk96TP5SCbgf2w==, tableContent=null), ArticleFig(id=1329457023424508131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, label=Figure 2, caption=
Robustness analysis, figureFileSmall=SoSoJGraRVmtXaVgdsK7XQ==, figureFileBig=yC1I5l6BGrXBv7pvih77fQ==, tableContent=null), ArticleFig(id=1329457023504199908, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, label=图2, caption=
鲁棒性分析, figureFileSmall=SoSoJGraRVmtXaVgdsK7XQ==, figureFileBig=yC1I5l6BGrXBv7pvih77fQ==, tableContent=null), ArticleFig(id=1329457023571308773, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, label=Figure 3, caption=
Pruning results for FOAD and its variants, figureFileSmall=JOR1grhSsnQsdEpyWeocCw==, figureFileBig=RGNGPCVaLJkx7qxdcMH7bg==, tableContent=null), ArticleFig(id=1329457023642611942, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, label=图3, caption=
FOAD及其变体的剪枝结果, figureFileSmall=JOR1grhSsnQsdEpyWeocCw==, figureFileBig=RGNGPCVaLJkx7qxdcMH7bg==, tableContent=null), ArticleFig(id=1329457023726498023, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, label=Figure 4, caption=
Analysis experimental results of hyperparameters t and s, figureFileSmall=0yrm7vzoCKzsXt4Z2+ZNgw==, figureFileBig=MRJv8FqUHPq7NzTWS+mAjQ==, tableContent=null), ArticleFig(id=1329457023797801192, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, label=图4, caption=
超参数t和s的分析实验结果, figureFileSmall=0yrm7vzoCKzsXt4Z2+ZNgw==, figureFileBig=MRJv8FqUHPq7NzTWS+mAjQ==, tableContent=null), ArticleFig(id=1329457023864910057, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, label=Table 1, caption=
Pruning Results of VGG-16 and ResNet-56 on CIFAR-10 Dataset
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 方法 | 精度/% | params | params.drop/% | FLOPs | FLOPs.drop/% |
|---|
| VGG-16 | L1[13](ICLR 2017) | 93.40 | 9.69×106 | 34.2 | 0.41280×109 | 34.2 |
| SSS[45](ECCV 2018) | 93.02 | 3.86×106 | 73.8 | 0.36638×109 | 41.6 |
| GAL[46](CPVR 2019) | 93.42 | 2.62×106 | 82.2 | 0.34379×109 | 45.2 |
| FPGM[29](CVPR 2019) | 93.54 | | | 0.41280×109 | 34.2 |
| Hinge[35](CVPR 2020) | 93.59 | 2.93×106 | 80.1 | 0.38206×109 | 39.1 |
| FOAD-O(t=1,s=0.3) | 94.00 | 6.89×106 | 53.2 | 0.39331×109 | 37.3 |
| FOAD-O(t=2,s=0.4) | 93.82 | 4.42×106 | 70.0 | 0.33932×109 | 45.9 |
| ThiNet[32](ICCV 2017) | 90.76 | 5.30×106 | 64.0 | 0.22585×109 | 64.0 |
| NS[20](ICCV 2017) | 93.80 | 1.69×106 | 88.5 | 0.30741×109 | 51.0 |
| HRank[22](CVPR 2020) | 92.34 | 2.63×106 | 82.1 | 0.21769×109 | 65.3 |
| Di[26](IJCAI 2022) | 93.27 | 2.13×106 | 85.5 | 0.26788×109 | 57.3 |
| FOAD-G | 93.81 | 1.90×106 | 87.1 | 0.22778×109 | 63.7 |
| FOAD-O(t=3,s=0.3) | 93.36 | 2.73×106 | 81.5 | 0.24684×109 | 60.7 |
| COP[31](IJCAI 2019) | 93.31 | 1.06×106 | 92.8 | 0.16625×109 | 73.5 |
| ABCPruner[38](IJCAI 2020) | 93.08 | 1.66×106 | 88.7 | 0.16499×109 | 73.7 |
| OTO[37](NeurIPS 2021) | 93.30 | 0.81×106 | 94.5 | 0.16813×109 | 73.2 |
| CHIP[25](NeurIPS 2021) | 93.18 | 1.87×106 | 87.3 | 0.13425×109 | 78.6 |
| Di[26](IJCAI 2022) | 93.08 | 1.02×106 | 93.1 | 0.16876×109 | 73.1 |
| FOAD-G | 93.41 | 0.74×106 | 95.0 | 0.17880×109 | 71.5 |
| FOAD-O(t=3,s=0.2) | 93.08 | 2.56×106 | 82.6 | 0.16562×109 | 73.6 |
| ResNet-56 | L1[13](ICLR 2017) | 93.06 | 0.59×106 | 27.6 | 0.21232×109 | 13.7 |
| PFA[24](CVPR 2018) | 92.49 | 0.49×106 | 40.4 | 0.15130×109 | 38.5 |
| NISP[47](CVPR 2018) | 93.01 | 0.47×106 | 42.4 | 0.15868×109 | 35.5 |
| GAL[46](CPVR 2019) | 92.98 | 0.72×106 | 11.8 | 0.16352×109 | 37.6 |
| FOAD-O(t=3,s=0.2) | 93.50 | 0.40×106 | 51.2 | 0.15186×109 | 38.3 |
| He[33](ICCV 2017) | 91.80 | | | 0.12301×109 | 50.0 |
| FOAD-G | 93.06 | 0.23×106 | 72.0 | 0.11809×109 | 52.0 |
| FOAD-O(t=3,s=0.1) | 92.59 | 0.38×106 | 53.7 | 0.12301×109 | 50.0 |
| CHIP[25](NeurIPS 2021) | 92.05 | 0.23×106 | 71.8 | 0.06815×109 | 72.3 |
| FOAD-G | 92.45 | 0.21×106 | 74.4 | 0.07627×109 | 69.0 |
| FOAD-O(t=4,s=0) | 91.20 | 0.29×106 | 64.6 | 0.07897×109 | 67.9 |
| HRank[22](CVPR 2020) | 90.72 | 0.26×106 | 68.1 | 0.06372×109 | 74.1 |
| FilterSketch[48](TNNLS 2021) | 91.20 | 0.23×106 | 71.8 | 0.06298×109 | 74.4 |
| FOAD-G | 91.34 | 0.15×106 | 81.7 | 0.05314×109 | 78.4 |
| FOAD-O(t=5,s=0) | 90.38 | 0.24×106 | 70.7 | 0.06495×109 | 73.6 |
), ArticleFig(id=1329457023948796138, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, label=表1, caption=
VGG-16和ResNet-56在CIFAR-10数据集上的修剪结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 方法 | 精度/% | params | params.drop/% | FLOPs | FLOPs.drop/% |
|---|
| VGG-16 | L1[13](ICLR 2017) | 93.40 | 9.69×106 | 34.2 | 0.41280×109 | 34.2 |
| SSS[45](ECCV 2018) | 93.02 | 3.86×106 | 73.8 | 0.36638×109 | 41.6 |
| GAL[46](CPVR 2019) | 93.42 | 2.62×106 | 82.2 | 0.34379×109 | 45.2 |
| FPGM[29](CVPR 2019) | 93.54 | | | 0.41280×109 | 34.2 |
| Hinge[35](CVPR 2020) | 93.59 | 2.93×106 | 80.1 | 0.38206×109 | 39.1 |
| FOAD-O(t=1,s=0.3) | 94.00 | 6.89×106 | 53.2 | 0.39331×109 | 37.3 |
| FOAD-O(t=2,s=0.4) | 93.82 | 4.42×106 | 70.0 | 0.33932×109 | 45.9 |
| ThiNet[32](ICCV 2017) | 90.76 | 5.30×106 | 64.0 | 0.22585×109 | 64.0 |
| NS[20](ICCV 2017) | 93.80 | 1.69×106 | 88.5 | 0.30741×109 | 51.0 |
| HRank[22](CVPR 2020) | 92.34 | 2.63×106 | 82.1 | 0.21769×109 | 65.3 |
| Di[26](IJCAI 2022) | 93.27 | 2.13×106 | 85.5 | 0.26788×109 | 57.3 |
| FOAD-G | 93.81 | 1.90×106 | 87.1 | 0.22778×109 | 63.7 |
| FOAD-O(t=3,s=0.3) | 93.36 | 2.73×106 | 81.5 | 0.24684×109 | 60.7 |
| COP[31](IJCAI 2019) | 93.31 | 1.06×106 | 92.8 | 0.16625×109 | 73.5 |
| ABCPruner[38](IJCAI 2020) | 93.08 | 1.66×106 | 88.7 | 0.16499×109 | 73.7 |
| OTO[37](NeurIPS 2021) | 93.30 | 0.81×106 | 94.5 | 0.16813×109 | 73.2 |
| CHIP[25](NeurIPS 2021) | 93.18 | 1.87×106 | 87.3 | 0.13425×109 | 78.6 |
| Di[26](IJCAI 2022) | 93.08 | 1.02×106 | 93.1 | 0.16876×109 | 73.1 |
| FOAD-G | 93.41 | 0.74×106 | 95.0 | 0.17880×109 | 71.5 |
| FOAD-O(t=3,s=0.2) | 93.08 | 2.56×106 | 82.6 | 0.16562×109 | 73.6 |
| ResNet-56 | L1[13](ICLR 2017) | 93.06 | 0.59×106 | 27.6 | 0.21232×109 | 13.7 |
| PFA[24](CVPR 2018) | 92.49 | 0.49×106 | 40.4 | 0.15130×109 | 38.5 |
| NISP[47](CVPR 2018) | 93.01 | 0.47×106 | 42.4 | 0.15868×109 | 35.5 |
| GAL[46](CPVR 2019) | 92.98 | 0.72×106 | 11.8 | 0.16352×109 | 37.6 |
| FOAD-O(t=3,s=0.2) | 93.50 | 0.40×106 | 51.2 | 0.15186×109 | 38.3 |
| He[33](ICCV 2017) | 91.80 | | | 0.12301×109 | 50.0 |
| FOAD-G | 93.06 | 0.23×106 | 72.0 | 0.11809×109 | 52.0 |
| FOAD-O(t=3,s=0.1) | 92.59 | 0.38×106 | 53.7 | 0.12301×109 | 50.0 |
| CHIP[25](NeurIPS 2021) | 92.05 | 0.23×106 | 71.8 | 0.06815×109 | 72.3 |
| FOAD-G | 92.45 | 0.21×106 | 74.4 | 0.07627×109 | 69.0 |
| FOAD-O(t=4,s=0) | 91.20 | 0.29×106 | 64.6 | 0.07897×109 | 67.9 |
| HRank[22](CVPR 2020) | 90.72 | 0.26×106 | 68.1 | 0.06372×109 | 74.1 |
| FilterSketch[48](TNNLS 2021) | 91.20 | 0.23×106 | 71.8 | 0.06298×109 | 74.4 |
| FOAD-G | 91.34 | 0.15×106 | 81.7 | 0.05314×109 | 78.4 |
| FOAD-O(t=5,s=0) | 90.38 | 0.24×106 | 70.7 | 0.06495×109 | 73.6 |
), ArticleFig(id=1329457024036876523, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, label=Table 2, caption=
Pruning Results of VGG-16 and ResNet-56 on CIFAR-100 Dataset
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 方法 | 精度 | params.drop | FLOPs.drop |
|---|
| VGG-16 | PFA[24](CVPR 2018) | 70.00 | 66.9 | 42.9 |
| COP[31](IJCAI 2019) | 71.77 | 73.2 | 43.1 |
| DPES[49](2021) | 67.06 | | 19.9 |
| CHIP[25](NeurIPS 2021) | 72.15 | 39.9 | 43.0 |
| Di[26](IJCAI 2022) | 72.00 | 80.4 | 56.5 |
| FOAD-G | 73.30 | 79.4 | 48.0 |
| FOAD-O(t=3,s=0.3) | 73.21 | 72.9 | 44.0 |
| ResNet-56 | PFA[24](CVPR 2018) | 69.22 | 18.5 | 20.6 |
| PFA[24](CVPR 2018) | 68.05 | 26.4 | 33.3 |
| DPES[49](IS 2021) | 57.81 | | 16.19 |
| CHIP[25](NeurIPS 2021) | 69.00 | 38.2 | 41.4 |
| PGMPF[50](AAAI 2022) | 70.21 | | 52.6 |
| FOAD-O(t=2,s=0.1) | 71.00 | 43.4 | 42.2 |
), ArticleFig(id=1329457024112373996, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, label=表2, caption=
VGG-16和ResNet-56在CIFAR-100数据集上的修剪结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | 方法 | 精度 | params.drop | FLOPs.drop |
|---|
| VGG-16 | PFA[24](CVPR 2018) | 70.00 | 66.9 | 42.9 |
| COP[31](IJCAI 2019) | 71.77 | 73.2 | 43.1 |
| DPES[49](2021) | 67.06 | | 19.9 |
| CHIP[25](NeurIPS 2021) | 72.15 | 39.9 | 43.0 |
| Di[26](IJCAI 2022) | 72.00 | 80.4 | 56.5 |
| FOAD-G | 73.30 | 79.4 | 48.0 |
| FOAD-O(t=3,s=0.3) | 73.21 | 72.9 | 44.0 |
| ResNet-56 | PFA[24](CVPR 2018) | 69.22 | 18.5 | 20.6 |
| PFA[24](CVPR 2018) | 68.05 | 26.4 | 33.3 |
| DPES[49](IS 2021) | 57.81 | | 16.19 |
| CHIP[25](NeurIPS 2021) | 69.00 | 38.2 | 41.4 |
| PGMPF[50](AAAI 2022) | 70.21 | | 52.6 |
| FOAD-O(t=2,s=0.1) | 71.00 | 43.4 | 42.2 |
), ArticleFig(id=1329457024217231597, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, label=Table 3, caption=
Pruning Results of MobileFaceNets on CASIA-WebFace Dataset
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | LFW精度/% | params | params.drop/% | FLOPs | FLOPs.drop/% |
|---|
| MobileFaceNets | 99.17 | 1.00×106 | 0 | 0.38×109 | 0 |
| FOAD-O(t=1,s=0) | 99.14 | 0.71×106 | 29.0 | 0.25×109 | 34.0 |
| FOAD-O(t=2,s=0) | 99.07 | 0.54×106 | 46.0 | 0.18×109 | 52.6 |
| FOAD-O(t=3,s=0) | 99.02 | 0.42×106 | 58.0 | 0.14×109 | 63.6 |
), ArticleFig(id=1329457024313700590, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, label=表3, caption=
MobileFaceNets在CASIA-WebFace数据集上的修剪结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型 | LFW精度/% | params | params.drop/% | FLOPs | FLOPs.drop/% |
|---|
| MobileFaceNets | 99.17 | 1.00×106 | 0 | 0.38×109 | 0 |
| FOAD-O(t=1,s=0) | 99.14 | 0.71×106 | 29.0 | 0.25×109 | 34.0 |
| FOAD-O(t=2,s=0) | 99.07 | 0.54×106 | 46.0 | 0.18×109 | 52.6 |
| FOAD-O(t=3,s=0) | 99.02 | 0.42×106 | 58.0 | 0.14×109 | 63.6 |
), ArticleFig(id=1329457024389198063, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, label=Table 4, caption=
Methods for Comparing the Similarity of Different Metric Feature Maps
, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | 度量方法 | 精度/% | params | params.drop/% | FLOPs | FLOPs.drop/% |
|---|
| CIFAR-10 | 余弦相似度 | 93.49 | 6.19×106 | 57.9 | 0.29×109 | 53.8 |
| 几何距离(本文) | 93.52 | 6.79×106 | 53.9 | 0.30×109 | 52.3 |
| CIFAR-100 | 余弦相似度 | 71.26 | 4.35×106 | 70.5 | 0.20×109 | 68.1 |
| 几何距离(本文) | 71.67 | 4.75×106 | 67.8 | 0.18×109 | 70.8 |
), ArticleFig(id=1329457024468889840, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, label=表4, caption=
对比不同度量特征图相似性的方法
, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | 度量方法 | 精度/% | params | params.drop/% | FLOPs | FLOPs.drop/% |
|---|
| CIFAR-10 | 余弦相似度 | 93.49 | 6.19×106 | 57.9 | 0.29×109 | 53.8 |
| 几何距离(本文) | 93.52 | 6.79×106 | 53.9 | 0.30×109 | 52.3 |
| CIFAR-100 | 余弦相似度 | 71.26 | 4.35×106 | 70.5 | 0.20×109 | 68.1 |
| 几何距离(本文) | 71.67 | 4.75×106 | 67.8 | 0.18×109 | 70.8 |
), ArticleFig(id=1329457024552775921, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=EN, label=Table 5, caption=
Analysis of the Effect of Different Batch Sizes on Model Pruning Performance
, figureFileSmall=null, figureFileBig=null, tableContent=
| Batch Size | 精度/% | params | FLOPs |
|---|
| 16 | 93.69 | 6.74×106 | 0.29793×109 |
| 32 | 93.56 | 6.58×106 | 0.29200×109 |
| 64 | 93.52 | 6.79×106 | 0.29929×109 |
| 128 | 93.48 | 6.89×106 | 0.30372×109 |
| 256 | 93.70 | 6.76×106 | 0.30235×109 |
| 512 | 93.46 | 6.78×106 | 0.30125×109 |
), ArticleFig(id=1329457024645050610, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329457012410265768, language=CN, label=表5, caption=
不同Batch Size对模型剪枝性能的影响分析
, figureFileSmall=null, figureFileBig=null, tableContent=
| Batch Size | 精度/% | params | FLOPs |
|---|
| 16 | 93.69 | 6.74×106 | 0.29793×109 |
| 32 | 93.56 | 6.58×106 | 0.29200×109 |
| 64 | 93.52 | 6.79×106 | 0.29929×109 |
| 128 | 93.48 | 6.89×106 | 0.30372×109 |
| 256 | 93.70 | 6.76×106 | 0.30235×109 |
| 512 | 93.46 | 6.78×106 | 0.30125×109 |
)], 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/issn1000-1239.202330085, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202330085, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202330085, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202330085, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1719763200000, fullTextJson=null, articleText=null, reference=null)