Generative Adversarial Networks

Generative Adversarial Networks is a type of generative model in deep learning that consists of two neural networks—a generator and a discriminator—engaged in a minimax game where the generator learns to produce realistic data samples by attempting to fool the discriminator, which in turn learns to distinguish between real and generated data.

10.4K

Publications

808.3K

Citations

36K

Authors

4.7K

Institutions

Publications per year

2017–2026

10.3K

Authors

36K

  1. JZ
    Jun-Yan Zhu

    Carnegie Mellon University, United States

    28 publications · 32.9K citations

    24

    h-index

  2. NS
    Nicu Sebe

    University of Trento, Italy

    31 publications · 1.7K citations

    21

    h-index

  3. DT
    Dacheng Tao

    The University of Sydney, Australia

    26 publications · 2.5K citations

    20

    h-index

  4. YB
    Yoshua Bengio

    Université de Montréal, Canada

    24 publications · 15.9K citations

    19

    h-index

  5. YL
    Yang Lei

    Emory University, United States

    25 publications · 1.9K citations

    19

    h-index

1–5 of 36K

Venues

  1. arXiv (Cornell University)

    Repository · 1.5K publications · 155.2K citations

    154

    h-index

  2. IEEE Access

    460 publications · 23.9K citations

    74

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 158 publications · 12.6K citations

    56

    h-index

  4. IEEE Transactions on Geoscience and Remote Sensing

    121 publications · 9.6K citations

    53

    h-index

  5. IEEE Transactions on Image Processing

    90 publications · 11.8K citations

    47

    h-index

1–5