Instance Discrimination

Instance Discrimination is a self-supervised learning framework that belongs to the class of contrastive representation learning methods, distinguished by its approach of treating each data sample as a unique category and training a model to discriminate between different instances of the same underlying data distribution through similarity in embedding space.

107

Publications

9.3K

Citations

436

Authors

125

Institutions

Publications per year

2017–2026

102

Authors

436

  1. SX
    Stella X. Yu

    University of California, Berkeley, United States

    8 publications · 3.9K citations

    8

    h-index

  2. ZW
    Zhirong Wu

    Microsoft Research Asia (China), China

    6 publications · 3.9K citations

    6

    h-index

  3. NZ
    Nanxuan Zhao

    City University of Hong Kong, Hong Kong SAR China

    4 publications · 143 citations

    4

    h-index

  4. PZ
    Pan Zhou

    National University of Singapore, Singapore

    4 publications · 530 citations

    4

    h-index

  5. DL
    Dahua Lin

    Chinese University of Hong Kong, Hong Kong SAR China

    3 publications · 3.8K citations

    3

    h-index

1–5 of 436

Venues

  1. arXiv (Cornell University)

    Repository · 35 publications · 1.6K citations

    20

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 6 publications · 259 citations

    6

    h-index

  3. 5

    h-index

  4. 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Conference · 4 publications · 487 citations

    4

    h-index

  5. 4

    h-index

1–5