Transformer-based Segmentation

Transformer-Based Segmentation is a semantic segmentation method that employs transformer architectures to model long-range contextual dependencies through self-attention mechanisms, distinguishing it from convolutional approaches by enabling global receptive fields and dynamic feature weighting.

659

Publications

69.5K

Citations

2.8K

Authors

710

Institutions

Publications per year

2017–2026

658

Authors

2.8K

  1. PL
    Ping Luo

    University of Hong Kong, Hong Kong SAR China

    11 publications · 7K citations

    11

    h-index

  2. EX
    Enze Xie

    University of Hong Kong, Hong Kong SAR China

    10 publications · 6.9K citations

    10

    h-index

  3. WW
    Wenhai Wang

    Nanjing University, China

    8 publications · 3.8K citations

    8

    h-index

  4. KY
    Kailun Yang

    Zhejiang University, China

    8 publications · 306 citations

    8

    h-index

  5. KP
    Kunyu Peng

    Karlsruhe Institute of Technology, Germany

    7 publications · 278 citations

    7

    h-index

1–5 of 2.8K

Venues

  1. arXiv (Cornell University)

    Repository · 117 publications · 14.4K citations

    42

    h-index

  2. 26

    h-index

  3. Remote Sensing

    30 publications · 2K citations

    26

    h-index

  4. 25

    h-index

  5. IEEE Transactions on Medical Imaging

    16 publications · 2.3K citations

    16

    h-index

1–5