Self-supervised Adaptation

Self-Supervised Adaptation is a methodological framework within Sim-To-Real Transfer that leverages unlabeled real-world data to automatically generate supervisory signals for aligning simulated and real-world representations without relying on manual annotations.

375

Publications

26.4K

Citations

1.7K

Authors

431

Institutions

Publications per year

2017–2026

349

Authors

1.7K

  1. AA
    Alexei A. Efros

    University of California, Berkeley, United States

    7 publications · 513 citations

    7

    h-index

  2. TD
    Trevor Darrell

    University of California, Berkeley, United States

    6 publications · 750 citations

    6

    h-index

  3. FW
    Fang Wen

    Microsoft Research Asia (China), China

    4 publications · 1K citations

    4

    h-index

  4. DC
    Dong Chen

    University of Science and Technology of China, China

    4 publications · 1K citations

    4

    h-index

  5. MY
    Ming–Hsuan Yang

    University of California, Merced, United States

    4 publications · 367 citations

    4

    h-index

1–5 of 1.7K

Venues

  1. arXiv (Cornell University)

    Repository · 69 publications · 4.1K citations

    30

    h-index

  2. 9

    h-index

  3. 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Conference · 9 publications · 5.8K citations

    9

    h-index

  4. IEEE Transactions on Medical Imaging

    9 publications · 364 citations

    9

    h-index

  5. 8

    h-index

1–5