Fully Supervised Segmentation

Fully Supervised Segmentation is an image segmentation paradigm that belongs to the class of supervised learning methods and is distinguished by its reliance on densely annotated pixel-level labels for training, enabling the model to learn precise mappings from input images to their corresponding segmentation masks.

102

Publications

16.8K

Citations

466

Authors

175

Institutions

Publications per year

2017–2026

97

Authors

466

  1. IL
    Issam Laradji

    University of British Columbia, Canada

    5 publications · 151 citations

    5

    h-index

  2. DV
    David Vázquez

    Universitat Autònoma de Barcelona, Spain

    4 publications · 123 citations

    4

    h-index

  3. AK
    Arnab Kumar Mondal

    Indian Institute of Technology Delhi, India

    3 publications · 160 citations

    3

    h-index

  4. RS
    Rainer Stiefelhagen

    Karlsruhe Institute of Technology, Germany

    3 publications · 165 citations

    3

    h-index

  5. CS
    Constantin Seibold

    Karlsruhe Institute of Technology, Germany

    3 publications · 165 citations

    3

    h-index

1–5 of 466

Venues

  1. arXiv (Cornell University)

    Repository · 24 publications · 1.3K citations

    15

    h-index

  2. IEEE Transactions on Medical Imaging

    7 publications · 594 citations

    7

    h-index

  3. Neurocomputing

    4 publications · 659 citations

    4

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 3 publications · 109 citations

    3

    h-index

  5. 3

    h-index

1–5