Focal Loss

Focal Loss is a modified cross-entropy loss function designed to address class imbalance by down-weighting the contribution of easy-to-classify examples and focusing training on hard, misclassified examples.

696

Publications

76.9K

Citations

3K

Authors

848

Institutions

Publications per year

2017–2026

581

Authors

3K

  1. WW
    Wenhai Wang

    Nanjing University, China

    4 publications · 1.4K citations

    5

    h-index

  2. CC
    Chen Change Loy

    Nanyang Technological University, Singapore

    5 publications · 689 citations

    5

    h-index

  3. JT
    Jinhui Tang

    Nanjing University of Science and Technology, China

    3 publications · 1.2K citations

    4

    h-index

  4. XH
    Xiaolin Hu

    Tsinghua University, China

    3 publications · 1.2K citations

    4

    h-index

  5. NK
    Naimul Khan

    Toronto Metropolitan University, Canada

    4 publications · 957 citations

    4

    h-index

1–5 of 3K

Venues

  1. IEEE Access

    40 publications · 2.1K citations

    28

    h-index

  2. arXiv (Cornell University)

    Repository · 36 publications · 3.2K citations

    21

    h-index

  3. Sensors

    23 publications · 1.1K citations

    20

    h-index

  4. Remote Sensing

    18 publications · 968 citations

    15

    h-index

  5. 12

    h-index

1–5