Self-supervised Image Representations

Self-Supervised Image Representations is a methodological framework in computer vision that learns discriminative visual features from unlabeled images by formulating pretext tasks that leverage the intrinsic structure of the data to generate supervisory signals.

327

Publications

40.2K

Citations

1.5K

Authors

421

Institutions

Publications per year

2017–2026

320

Authors

1.5K

  1. YL
    Yann LeCun

    New York University, United States

    7 publications · 386 citations

    7

    h-index

  2. SK
    Simon Kornblith

    Google (United States), United States

    5 publications · 7.8K citations

    5

    h-index

  3. MB
    Michael B. Gotway

    University of California, San Francisco, United States

    5 publications · 295 citations

    5

    h-index

  4. NH
    Neil Houlsby

    Google (United States), United States

    5 publications · 773 citations

    5

    h-index

  5. IM
    Ishan Misra

    Meta (Israel), Israel

    5 publications · 5.4K citations

    5

    h-index

1–5 of 1.5K

Venues

  1. arXiv (Cornell University)

    Repository · 83 publications · 15.7K citations

    34

    h-index

  2. 17

    h-index

  3. 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Conference · 15 publications · 6.1K citations

    14

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 12 publications · 421 citations

    12

    h-index

  5. Medical Image Analysis

    8 publications · 1.1K citations

    8

    h-index

1–5