Self-supervised Segmentation

Self-Supervised Segmentation is a machine learning approach within semantic segmentation that leverages unlabeled data by generating pseudo-supervisory signals through pretext tasks, thereby distinguishing itself from fully supervised methods by eliminating the reliance on manually annotated ground truth labels.

224

Publications

11.4K

Citations

961

Authors

336

Institutions

Publications per year

2017–2026

211

Authors

961

  1. WS
    Wei Shen

    Shanghai University, China

    3 publications · 295 citations

    3

    h-index

  2. LV
    Luc Van Gool

    ETH Zurich, Switzerland

    3 publications · 176 citations

    3

    h-index

  3. ZZ
    Zhun Zhong

    University of Trento, Italy

    3 publications · 163 citations

    3

    h-index

  4. DD
    Dengxin Dai

    ETH Zurich, Switzerland

    3 publications · 176 citations

    3

    h-index

  5. FW
    Fang Wen

    Microsoft Research Asia (China), China

    3 publications · 558 citations

    3

    h-index

1–5 of 961

Venues

  1. arXiv (Cornell University)

    Repository · 35 publications · 972 citations

    18

    h-index

  2. 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Conference · 9 publications · 732 citations

    9

    h-index

  3. IEEE Transactions on Medical Imaging

    9 publications · 535 citations

    9

    h-index

  4. 5

    h-index

  5. Medical Image Analysis

    4 publications · 311 citations

    4

    h-index

1–5