Open-set Image Classification

Open-Set Image Classification is an image classification paradigm that, unlike traditional closed-set settings, explicitly accounts for the presence of unknown classes during testing by requiring the model to not only correctly classify known classes but also to effectively reject samples from unseen categories.

55

Publications

3.9K

Citations

241

Authors

88

Institutions

Publications per year

2017–2026

51

Authors

241

  1. JY
    Junjie Yan

    Group Sense (China), China

    3 publications · 257 citations

    3

    h-index

  2. DL
    Ding Liang

    University of Hong Kong, Hong Kong SAR China

    3 publications · 257 citations

    3

    h-index

  3. VM
    Vishal M. Patel

    Johns Hopkins University, United States

    3 publications · 442 citations

    3

    h-index

  4. XH
    Xiaolin Hu

    Tsinghua University, China

    3 publications · 257 citations

    3

    h-index

  5. LF
    Leyuan Fang

    Hunan University, China

    3 publications · 160 citations

    3

    h-index

1–5 of 241

Venues

  1. arXiv (Cornell University)

    Repository · 7 publications · 260 citations

    7

    h-index

  2. 4

    h-index

  3. IEEE Geoscience and Remote Sensing Letters

    GRSL · 2 publications · 41 citations

    2

    h-index

  4. Pattern Recognition

    2 publications · 69 citations

    2

    h-index

  5. Expert Systems with Applications

    2 publications · 52 citations

    2

    h-index

1–5