Instance Mask Refinement

Instance Mask Refinement is a post-processing technique in instance segmentation that iteratively enhances the spatial accuracy and boundary precision of predicted object masks by optimizing their pixel-level confidence scores under learned or geometric constraints.

42

Publications

2.7K

Citations

164

Authors

70

Institutions

Publications per year

2017–2026

38

Authors

164

  1. YX
    Yuwen Xiong

    University of Toronto, Canada

    3 publications · 268 citations

    3

    h-index

  2. JF
    Jiashi Feng

    National University of Singapore, Singapore

    3 publications · 140 citations

    3

    h-index

  3. TL
    Tsung-Yi Lin

    Google (United States), United States

    3 publications · 206 citations

    3

    h-index

  4. RU
    Raquel Urtasun

    University of Toronto, Canada

    3 publications · 268 citations

    3

    h-index

  5. MR
    Matthew R. Scott

    MSIGHT Technologies (China), China

    2 publications · 73 citations

    2

    h-index

1–5 of 164

Venues

  1. arXiv (Cornell University)

    Repository · 7 publications · 155 citations

    7

    h-index

  2. Remote Sensing

    2 publications · 157 citations

    2

    h-index

  3. 2022 IEEE International Conference on Multimedia and Expo (ICME)

    Conference · 1 publications · 39 citations

    1

    h-index

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

    Conference · 1 publications · 138 citations

    1

    h-index

  5. 1

    h-index

1–5