Unsupervised Transfer Learning

Unsupervised Transfer Learning is a transfer learning paradigm in which knowledge is transferred from a source domain to a target domain without relying on labeled data in the target domain, distinguishing itself from supervised and semi-supervised transfer learning by the absence of label supervision during adaptation.

629

Publications

53.3K

Citations

2.1K

Authors

660

Institutions

Publications per year

2017–2026

574

Authors

2.1K

  1. JL
    Jian Liang

    Chinese Academy of Sciences, China

    7 publications · 537 citations

    7

    h-index

  2. JL
    Jie Lü

    University of Technology Sydney, Australia

    6 publications · 324 citations

    6

    h-index

  3. RH
    Ran He

    Institute of Automation, China

    6 publications · 514 citations

    6

    h-index

  4. LW
    Lior Wolf

    Tel Aviv University, Israel

    6 publications · 586 citations

    6

    h-index

  5. KS
    Kate Saenko

    University of California, Berkeley, United States

    5 publications · 2.4K citations

    5

    h-index

1–5 of 2.1K

Venues

  1. arXiv (Cornell University)

    Repository · 86 publications · 6.7K citations

    35

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 23 publications · 1.2K citations

    20

    h-index

  3. IEEE Transactions on Multimedia

    15 publications · 780 citations

    15

    h-index

  4. IEEE Transactions on Image Processing

    15 publications · 1.1K citations

    14

    h-index

  5. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 10 publications · 1.3K citations

    10

    h-index

1–5