Domain Generalization

Domain Generalization is a transfer learning approach that seeks to learn domain-invariant representations from multiple source domains to enable effective model performance on unseen target domains with distinct data distributions, distinguishing itself by focusing on generalization across domains rather than adaptation to specific ones.

1.1K

Publications

87.7K

Citations

3.7K

Authors

759

Institutions

Publications per year

2017–2026

966

Authors

3.7K

  1. DT
    Dacheng Tao

    The University of Sydney, Australia

    12 publications · 827 citations

    12

    h-index

  2. KZ
    Kaiyang Zhou

    Nanyang Technological University, Singapore

    12 publications · 3.4K citations

    12

    h-index

  3. HL
    Haoliang Li

    Nanyang Technological University, Singapore

    11 publications · 1.9K citations

    11

    h-index

  4. YY
    Yongxin Yang

    University of Edinburgh, United Kingdom

    11 publications · 4K citations

    11

    h-index

  5. YS
    Yinghuan Shi

    Nanjing University, China

    10 publications · 376 citations

    10

    h-index

1–5 of 3.7K

Venues

  1. arXiv (Cornell University)

    Repository · 226 publications · 13.9K citations

    55

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 43 publications · 5.1K citations

    31

    h-index

  3. 24

    h-index

  4. IEEE Transactions on Image Processing

    24 publications · 1.8K citations

    22

    h-index

  5. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 24 publications · 3.1K citations

    22

    h-index

1–5