Contrasting Contrastive Self-Supervised Representation Learning Pipelines

被引:10
|
作者
Kotar, Klemen [1 ]
Ilharco, Gabriel [2 ]
Schmidt, Ludwig [2 ]
Ehsani, Kiana [1 ]
Mottaghi, Roozbeh [1 ,2 ]
机构
[1] PRIOR Allen Inst AI, Seattle, WA 98103 USA
[2] Univ Washington, Seattle, WA 98195 USA
关键词
D O I
10.1109/ICCV48922.2021.00980
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the past few years, we have witnessed remarkable breakthroughs in self-supervised representation learning. Despite the success and adoption of representations learned through this paradigm, much is yet to be understood about how different training methods and datasets influence performance on downstream tasks. In this paper, we analyze contrastive approaches as one of the most successful and popular variants of self-supervised representation learning. We perform this analysis from the perspective of the training algorithms, pre-training datasets and end tasks. We examine over 700 training experiments including 30 encoders, 4 pre-training datasets and 20 diverse downstream tasks. Our experiments address various questions regarding the performance of self-supervised models compared to their supervised counterparts, current benchmarks used for evaluation, and the effect of the pre-training data on end task performance. Our Visual Representation Benchmark (ViRB) is available at: https://github.com/allenai/virb.
引用
收藏
页码:9929 / 9939
页数:11
相关论文
共 50 条
  • [21] Pose-disentangled Contrastive Learning for Self-supervised Facial Representation
    Liu, Yuanyuan
    Wang, Wenbin
    Zhan, Yibing
    Feng, Shaoze
    Liu, Kejun
    Chen, Zhe
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 9717 - 9728
  • [22] Self-Supervised Video Representation Learning with Meta-Contrastive Network
    Lin, Yuanze
    Guo, Xun
    Lu, Yan
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 8219 - 8229
  • [23] Self-supervised contrastive representation learning for classifying Internet of Things malware
    Wang, Fangwei
    Chen, Yinhe
    Gao, Hongfeng
    Li, Qingru
    Wang, Changguang
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2025, 150
  • [24] Adversarial Self-Supervised Contrastive Learning
    Kim, Minseon
    Tack, Jihoon
    Hwang, Sung Ju
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS (NEURIPS 2020), 2020, 33
  • [25] A Survey on Contrastive Self-Supervised Learning
    Jaiswal, Ashish
    Babu, Ashwin Ramesh
    Zadeh, Mohammad Zaki
    Banerjee, Debapriya
    Makedon, Fillia
    TECHNOLOGIES, 2021, 9 (01)
  • [26] Self-Supervised Learning: Generative or Contrastive
    Liu, Xiao
    Zhang, Fanjin
    Hou, Zhenyu
    Mian, Li
    Wang, Zhaoyu
    Zhang, Jing
    Tang, Jie
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (01) : 857 - 876
  • [27] Contrastive and Non-Contrastive Strategies for Federated Self-Supervised Representation Learning and Deep Clustering
    Miao, Runxuan
    Koyuncu, Erdem
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2024, 18 (06) : 1070 - 1084
  • [28] Cut-in maneuver detection with self-supervised contrastive video representation learning
    Nalcakan, Yagiz
    Bastanlar, Yalin
    SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (06) : 2915 - 2923
  • [29] SELF-SUPERVISED CONTRASTIVE LEARNING FOR CROSS-DOMAIN HYPERSPECTRAL IMAGE REPRESENTATION
    Lee, Hyungtae
    Kwon, Heesung
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 3239 - 3243
  • [30] Cross-View Temporal Contrastive Learning for Self-Supervised Video Representation
    Wang, Lulu
    Xu, Zengmin
    Zhang, Xuelian
    Meng, Ruxing
    Lu, Tao
    Computer Engineering and Applications, 2024, 60 (18) : 158 - 166