Unsupervised Instance Segmentation

Unsupervised Instance Segmentation is an instance segmentation paradigm that, unlike its supervised counterparts, operates without relying on manually annotated ground-truth instance masks during model training, thereby achieving the separation and localization of distinct object instances through unsupervised learning mechanisms.

57

Publications

3.1K

Citations

243

Authors

113

Institutions

Publications per year

2017–2026

51

Authors

243

  1. AF
    Alireza Fathi

    Babol University of Medical Sciences, Iran

    2 publications · 126 citations

    2

    h-index

  2. XW
    Xudong Wang

    Shanghai Jiao Tong University, China

    2 publications · 179 citations

    2

    h-index

  3. IM
    Ishan Misra

    Meta (Israel), Israel

    2 publications · 179 citations

    2

    h-index

  4. RG
    Rohit Girdhar

    Carnegie Mellon University, United States

    2 publications · 179 citations

    2

    h-index

  5. SX
    Stella X. Yu

    University of California, Berkeley, United States

    2 publications · 179 citations

    2

    h-index

1–5 of 243

Venues

  1. arXiv (Cornell University)

    Repository · 4 publications · 46 citations

    4

    h-index

  2. Biosystems Engineering

    3 publications · 153 citations

    3

    h-index

  3. Expert Systems with Applications

    3 publications · 115 citations

    3

    h-index

  4. Computers and Electronics in Agriculture

    4 publications · 91 citations

    3

    h-index

  5. 2

    h-index

1–5