Transferable Representation Learning

Transferable Representation Learning is a meta-learning approach that enables the acquisition of feature representations across tasks or domains such that the learned knowledge can be effectively adapted to novel, previously unseen tasks with minimal additional training.

1.4K

Publications

145.1K

Citations

4.8K

Authors

1K

Institutions

Publications per year

2017–2026

1.2K

Authors

4.8K

  1. ML
    Mingsheng Long

    Tsinghua University, China

    19 publications · 8.3K citations

    18

    h-index

  2. JW
    Jianmin Wang

    Tsinghua University, China

    19 publications · 8.3K citations

    18

    h-index

  3. MI
    Michael I. Jordan

    University of California, Berkeley, United States

    13 publications · 7.1K citations

    13

    h-index

  4. YB
    Yoshua Bengio

    Université de Montréal, Canada

    11 publications · 5.3K citations

    11

    h-index

  5. QY
    Qiang Yang

    Hong Kong University of Science and Technology, Hong Kong SAR China

    11 publications · 1.4K citations

    11

    h-index

1–5 of 4.8K

Venues

  1. arXiv (Cornell University)

    Repository · 323 publications · 31.3K citations

    70

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 42 publications · 3.5K citations

    27

    h-index

  3. 22

    h-index

  4. IEEE Transactions on Image Processing

    23 publications · 1.2K citations

    19

    h-index

  5. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 22 publications · 2.7K citations

    18

    h-index

1–5