Adversarial Loss

Adversarial Loss is a type of loss function used in machine learning that quantifies the discrepancy between a model's predictions and the desired adversarial objectives, typically by measuring the divergence between real and generated data distributions in a minimax game framework.

1.2K

Publications

148.2K

Citations

4.3K

Authors

907

Institutions

Publications per year

2017–2026

1.2K

Authors

4.3K

  1. MY
    Ming–Hsuan Yang

    University of California, Merced, United States

    9 publications · 1.8K citations

    9

    h-index

  2. PH
    Pheng‐Ann Heng

    Chinese University of Hong Kong, Hong Kong SAR China

    9 publications · 1.4K citations

    9

    h-index

  3. RH
    Ran He

    Institute of Automation, China

    8 publications · 1.2K citations

    8

    h-index

  4. PK
    Pushmeet Kohli

    Microsoft Research (United Kingdom), United Kingdom

    7 publications · 876 citations

    7

    h-index

  5. SG
    Sven Gowal

    Google (United States), United States

    6 publications · 859 citations

    6

    h-index

1–5 of 4.3K

Venues

  1. arXiv (Cornell University)

    Repository · 300 publications · 31.2K citations

    76

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 27 publications · 2K citations

    20

    h-index

  3. IEEE Access

    36 publications · 1.3K citations

    19

    h-index

  4. IEEE Transactions on Image Processing

    22 publications · 3.4K citations

    19

    h-index

  5. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 25 publications · 4.5K citations

    19

    h-index

1–5