Concepedia

Distribution Shift

Distribution Shift is a phenomenon in statistical learning where the underlying probability distribution of input data changes between training and deployment environments, leading to potential model performance degradation due to the discrepancy between the source and target distributions.

320

Publications

19K

Citations

1.3K

Authors

360

Institutions

Publications per year

2017–2026

286

Variants

Dataset Shift

Parents

Publications

320

The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

Dan Hendrycks, Steven Basart, Norman Mu et al. · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 1K citations

, , +10

FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation

Judy Hoffman, Dequan Wang, Fisher Yu et al. · arXiv (Cornell University) · 2016 · 695 citations · Full text

, , +16

Big Self-Supervised Models Advance Medical Image Classification

Shekoofeh Azizi, Basil Mustafa, Fiona Ryan et al. · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 2021 · 609 citations

, , +17

Joint Geometrical and Statistical Alignment for Visual Domain Adaptation

Jing Zhang, Wanqing Li, Philip Ogunbona · 2017 · 590 citations

, , +10

Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data

Yen-Chang Hsu, Yilin Shen, Hongxia Jin et al. · 2020 · 463 citations

, , +15

1–5 of 320

Authors

1.3K

  1. KK
    Kun Kuang

    Zhejiang University, China

    6 publications · 449 citations

    6

    h-index

  2. CF
    Chelsea Finn

    University of California, Berkeley, United States

    6 publications · 245 citations

    6

    h-index

  3. SL
    Sergey Levine

    University of California, Berkeley, United States

    6 publications · 263 citations

    6

    h-index

  4. MS
    Masashi Sugiyama

    Tokyo Institute of Technology, Japan

    6 publications · 216 citations

    6

    h-index

  5. BS
    Bernhard Schölkopf

    Max Planck Institute for Intelligent Systems, Germany

    5 publications · 216 citations

    5

    h-index

1–5 of 1.3K

Institutions

360

  1. Carnegie Mellon University

    Pittsburgh, United States

    14 h-index

    40 publications

    2.5K citations

  2. Tsinghua University

    Beijing, China

    13 h-index

    33 publications

    2K citations

  3. Google (United States)

    Mountain View, United States

    13 h-index

    59 publications

    12.3K citations

  4. University of California, Berkeley

    Berkeley, United States

    13 h-index

    48 publications

    11K citations

  5. Stanford University

    Stanford, United States

    11 h-index

    29 publications

    1.6K citations

  6. National University of Singapore

    Singapore, Singapore

    8 h-index

    17 publications

    1.1K citations

  7. Chinese Academy of Sciences

    Beijing, China

    7 h-index

    17 publications

    621 citations

  8. Nanjing University

    Nanjing, China

    7 h-index

    11 publications

    881 citations

1–8 of 360

Venues

  1. arXiv (Cornell University)

    Repository · 97 publications · 4.6K citations

    36

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 13 publications · 622 citations

    12

    h-index

  3. 8

    h-index

  4. 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Conference · 6 publications · 2K citations

    6

    h-index

  5. 5

    h-index

1–5