Mutual Contrastive Learning for Visual Representation Learning

被引:0
|
作者
Yang, Chuanguang [1 ,2 ]
An, Zhulin [1 ]
Cai, Linhang [1 ,2 ]
Xu, Yongjun [1 ]
机构
[1] Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
[2] Univ Chinese Acad Sci, Beijing, Peoples R China
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present a collaborative learning method called Mutual Contrastive Learning (MCL) for general visual representation learning. The core idea of MCL is to perform mutual interaction and transfer of contrastive distributions among a cohort of networks. A crucial component of MCL is Interactive Contrastive Learning (ICL). Compared with vanilla contrastive learning, ICL can aggregate cross-network embedding information and maximize the lower bound to the mutual information between two networks. This enables each network to learn extra contrastive knowledge from others, leading to better feature representations for visual recognition tasks. We emphasize that the resulting MCL is conceptually simple yet empirically powerful. It is a generic framework that can be applied to both supervised and self-supervised representation learning. Experimental results on image classification and transfer learning to object detection show that MCL can lead to consistent performance gains, demonstrating that MCL can guide the network to generate better feature representations. Code is available at https://github.com/winycg/MCL.
引用
收藏
页码:3045 / 3053
页数:9
相关论文
共 50 条
  • [1] Decomposed Mutual Information Estimation for Contrastive Representation Learning
    Sordoni, Alessandro
    Dziri, Nouha
    Schulz, Hannes
    Gordon, Geoff
    Bachman, Phil
    Tachet, Remi
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [2] Multimodal Contrastive Training for Visual Representation Learning
    Yuan, Xin
    Lin, Zhe
    Kuen, Jason
    Zhang, Jianming
    Wang, Yilin
    Maire, Michael
    Kale, Ajinkya
    Faieta, Baldo
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 6991 - 7000
  • [3] When Does Contrastive Visual Representation Learning Work?
    Cole, Elijah
    Yang, Xuan
    Wilber, Kimberly
    Mac Aodha, Oisin
    Belongie, Serge
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 14735 - 14744
  • [4] A Sensorimotor Perspective on Contrastive Multiview Visual Representation Learning
    Laflaquiere, Alban
    [J]. IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2022, 14 (02) : 269 - 278
  • [5] Mutual Information Driven Equivariant Contrastive Learning for 3D Action Representation Learning
    Lin, Lilang
    Zhang, Jiahang
    Liu, Jiaying
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 1883 - 1897
  • [6] Unsupervised Galaxy Morphological Visual Representation with Deep Contrastive Learning
    Wei, Shoulin
    Li, Yadi
    Lu, Wei
    Li, Nan
    Liang, Bo
    Dai, Wei
    Zhang, Zhijian
    [J]. PUBLICATIONS OF THE ASTRONOMICAL SOCIETY OF THE PACIFIC, 2022, 134 (1041)
  • [7] Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition
    Yang, Chuanguang
    An, Zhulin
    Zhou, Helong
    Zhuang, Fuzhen
    Xu, Yongjun
    Zhang, Qian
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (08) : 10212 - 10227
  • [8] Masked Contrastive Representation Learning for Reinforcement Learning
    Zhu, Jinhua
    Xia, Yingce
    Wu, Lijun
    Deng, Jiajun
    Zhou, Wengang
    Qin, Tao
    Liu, Tie-Yan
    Li, Houqiang
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (03) : 3421 - 3433
  • [9] Contrastive Code Representation Learning
    Jain, Paras
    Jain, Ajay
    Zhang, Tianjun
    Abbeel, Pieter
    Gonzalez, Joseph E.
    Stoica, Ion
    [J]. 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 5954 - 5971
  • [10] Contrastive Cross-Modal Representation Learning Based Active Learning for Visual Question Answer
    Zhang B.-C.
    Li L.
    Zha Z.-J.
    Huang Q.-M.
    [J]. Jisuanji Xuebao/Chinese Journal of Computers, 2022, 45 (08): : 1730 - 1745