收藏切换
Semantic Contrastive Clustering with Federated Data Augmentation
收藏切换
Qihong Wang, Hongjie Jia*, Longxia Huang, Qirong Mao
Journal of Computer Research and Development | 2024, 61(6) : 1511 - 1524
Less
收藏切换
Journal of Computer Research and Development | 2024, 61(6): 1511-1524
• Artificial Intelligence •
Semantic Contrastive Clustering with Federated Data Augmentation
Full
Qihong Wang, Hongjie Jia*, Longxia Huang, Qirong Mao
Affiliations
  • School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013
  • born in 1999. Master candidate. His main research interest includes deep clustering

    born in 1988. PhD, associate professor. His main research interests include data clustering, deep learning, and pattern recognition

    born in 1991. PhD, associate professor. Her main research interests include privacy protection, data sharing, and cloud computing. ()

    born in 1975. PhD, professor, PhD supervisor. Member of IEEE and ACM. Her main research interests include affective computing, pattern recognition, and multimedia analysis. ()

About Author:

born in 1999. Master candidate. His main research interest includes deep clustering

born in 1988. PhD, associate professor. His main research interests include data clustering, deep learning, and pattern recognition

born in 1991. PhD, associate professor. Her main research interests include privacy protection, data sharing, and cloud computing. ()

born in 1975. PhD, professor, PhD supervisor. Member of IEEE and ACM. Her main research interests include affective computing, pattern recognition, and multimedia analysis. ()

Published: 2024-06-01 doi: 10.7544/issn1000-1239.202220995
Outline
收藏切换

Given the excellent performance of contrastive learning on downstream tasks, contrastive clustering has received much more attention recently. However, most approaches only utilize a simple kind of data augmentation. Although augmented views keep the majority of information from original samples, they also inherit a mixture of characteristic of features, including semantic and non-semantic features, which limits model’s learning ability of semantic information under similar or identical view patterns. Even some approaches regard two different augmentation views being from the same sample and keeping similar view patterns as positive pairs, which results in sample pairs lacking of semantics. In this paper, we propose a semantic contrastive clustering method with federated data augmentation to solve these problems. Two different types of data augmentations, namely strong data augmentation and weak data augmentation, are introduced to produce two very different view patterns. These two view patterns are utilized to mitigate the disturbance of non-semantic information and improve the semantic awareness of the proposed approach. Moreover, a global k-nearest neighbor graph is used to bring global category information, which instructs the model to treat different samples from the same cluster as positive pairs. Extensive experiments on six commonly used and challenging image datasets show that the proposed method achieves the state-of-the-art performance and confirms the superiority and validity of it.

strong data augmentation  /  weak data augmentation  /  contrastive learning  /  global category information  /  clustering
王气洪, 贾洪杰, 黄龙霞, 毛启容. 联合数据增强的语义对比聚类. 计算机研究与发展, 2024 , 61 (6) : 1511 -1524 . DOI: 10.7544/issn1000-1239.202220995
Qihong Wang, Hongjie Jia, Longxia Huang, Qirong Mao. Semantic Contrastive Clustering with Federated Data Augmentation[J]. Journal of Computer Research and Development, 2024 , 61 (6) : 1511 -1524 . DOI: 10.7544/issn1000-1239.202220995
Year 2024 volume 61 Issue 6
75
36
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202220995
  • Receive Date:2022-12-07
  • Online Date:2026-11-17
  • Published:2024-06-01
Article Data
Affiliations
History
  • Received:2022-12-07
  • Revised:2023-08-15
Affiliations
    School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202220995
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT