Fully Convolutional Networks

Fully Convolutional Networks is a deep learning model architecture for semantic segmentation that replaces fully connected layers with convolutional layers to enable end-to-end pixel-wise prediction.

2.6K

Publications

401.5K

Citations

9.2K

Authors

2K

Institutions

Publications per year

2017–2026

2.4K

Variants

Fcns

Authors

9.2K

  1. CS
    Chunhua Shen

    The University of Adelaide, Australia

    32 publications · 13.8K citations

    25

    h-index

  2. DS
    Dinggang Shen

    University of North Carolina at Chapel Hill, United States

    23 publications · 3.1K citations

    19

    h-index

  3. HL
    Huchuan Lu

    Dalian University of Technology, China

    18 publications · 5.9K citations

    18

    h-index

  4. HC
    Hao Chen

    Chinese University of Hong Kong, Hong Kong SAR China

    19 publications · 9.8K citations

    17

    h-index

  5. AY
    Alan Yuille

    Johns Hopkins University, United States

    19 publications · 6.2K citations

    15

    h-index

1–5 of 9.2K

Venues

  1. arXiv (Cornell University)

    Repository · 371 publications · 55.7K citations

    84

    h-index

  2. IEEE Access

    98 publications · 6.5K citations

    43

    h-index

  3. Remote Sensing

    81 publications · 5.3K citations

    42

    h-index

  4. Neurocomputing

    42 publications · 3.9K citations

    29

    h-index

  5. Sensors

    50 publications · 4.4K citations

    28

    h-index

1–5