Semi-supervised Instance Segmentation

Semi-Supervised Instance Segmentation is an instance segmentation framework that leverages a limited set of fully annotated training samples alongside a larger pool of unlabeled or weakly labeled data to learn pixel-level object masks, distinguishing itself from fully supervised methods by reducing annotation dependency through semi-supervised learning strategies.

73

Publications

4K

Citations

372

Authors

156

Institutions

Publications per year

2017–2026

68

Authors

372

  1. CY
    Chenyu You

    Yale University, United States

    3 publications · 175 citations

    3

    h-index

  2. CS
    Cordelia Schmid

    Institut national de recherche en sciences et technologies du numérique, France

    2 publications · 710 citations

    2

    h-index

  3. SZ
    Shoujun Zhou

    Chinese Academy of Sciences, China

    2 publications · 91 citations

    2

    h-index

  4. LC
    Liujuan Cao

    Xiamen University, China

    2 publications · 56 citations

    2

    h-index

  5. VB
    Vasileios Belagiannis

    Technical University of Munich, Germany

    2 publications · 307 citations

    2

    h-index

1–5 of 372

Venues

  1. arXiv (Cornell University)

    Repository · 8 publications · 807 citations

    8

    h-index

  2. Medical Image Analysis

    5 publications · 563 citations

    5

    h-index

  3. Computers in Biology and Medicine

    3 publications · 106 citations

    3

    h-index

  4. 3

    h-index

  5. 3

    h-index

1–5