Visual Transfer Learning

Visual Transfer Learning is a transfer learning paradigm that leverages knowledge acquired from a source visual domain to improve learning performance in a target visual domain with differing data distributions, thereby distinguishing itself by its focus on cross-domain visual representation adaptation.

212

Publications

22.2K

Citations

727

Authors

245

Institutions

Publications per year

2017–2026

168

Authors

727

  1. TD
    Trevor Darrell

    University of California, Berkeley, United States

    8 publications · 1.9K citations

    8

    h-index

  2. JH
    Judy Hoffman

    University of California, Berkeley, United States

    6 publications · 1.3K citations

    6

    h-index

  3. CL
    Chunyuan Li

    Microsoft Research (United Kingdom), United Kingdom

    5 publications · 211 citations

    5

    h-index

  4. LY
    Lu Yuan

    Microsoft Research (United Kingdom), United Kingdom

    5 publications · 725 citations

    5

    h-index

  5. AA
    Alexei A. Efros

    University of California, Berkeley, United States

    5 publications · 1K citations

    5

    h-index

1–5 of 727

Venues

  1. arXiv (Cornell University)

    Repository · 54 publications · 3.8K citations

    28

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 8 publications · 361 citations

    8

    h-index

  3. 6

    h-index

  4. 5

    h-index

  5. 5

    h-index

1–5