TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/CB Loss

CB Loss

Reported on 10 benchmarks across 5 tasks · 1 paper · 10 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology6 results

  • Generalized Few-Shot ClassificationonEGTEA
    Average Precision· 2019-01-16
    63.39
    best: 63.86 (CDB-loss (3D- ResNeXt101))
    SOTA
    Class-Balanced Loss Based on Effective Number of SamplesarXiv:1901.05555
  • Generalized Few-Shot ClassificationonEGTEA
    Average Recall· 2019-01-16
    63.26
    best: 66.24 (CDB-loss (3D- ResNeXt101))
    SOTA
    Class-Balanced Loss Based on Effective Number of SamplesarXiv:1901.05555
  • Long-tail LearningonEGTEA
    Average Precision· 2019-01-16
    63.39
    best: 63.86 (CDB-loss (3D- ResNeXt101))
    SOTA
    Class-Balanced Loss Based on Effective Number of SamplesarXiv:1901.05555
  • Long-tail LearningonEGTEA
    Average Recall· 2019-01-16
    63.26
    best: 66.24 (CDB-loss (3D- ResNeXt101))
    SOTA
    Class-Balanced Loss Based on Effective Number of SamplesarXiv:1901.05555
  • Generalized Few-Shot LearningonEGTEA
    Average Precision· 2019-01-16
    63.39
    best: 63.86 (CDB-loss (3D- ResNeXt101))
    SOTA
    Class-Balanced Loss Based on Effective Number of SamplesarXiv:1901.05555
  • Generalized Few-Shot LearningonEGTEA
    Average Recall· 2019-01-16
    63.26
    best: 66.24 (CDB-loss (3D- ResNeXt101))
    SOTA
    Class-Balanced Loss Based on Effective Number of SamplesarXiv:1901.05555

Computer Vision4 results

  • Image ClassificationonEGTEA
    Average Precision· 2019-01-16
    63.39
    best: 63.86 (CDB-loss (3D- ResNeXt101))
    SOTA
    Class-Balanced Loss Based on Effective Number of SamplesarXiv:1901.05555
  • Image ClassificationonEGTEA
    Average Recall· 2019-01-16
    63.26
    best: 66.24 (CDB-loss (3D- ResNeXt101))
    SOTA
    Class-Balanced Loss Based on Effective Number of SamplesarXiv:1901.05555
  • Few-Shot Image ClassificationonEGTEA
    Average Precision· 2019-01-16
    63.39
    best: 63.86 (CDB-loss (3D- ResNeXt101))
    SOTA
    Class-Balanced Loss Based on Effective Number of SamplesarXiv:1901.05555
  • Few-Shot Image ClassificationonEGTEA
    Average Recall· 2019-01-16
    63.26
    best: 66.24 (CDB-loss (3D- ResNeXt101))
    SOTA
    Class-Balanced Loss Based on Effective Number of SamplesarXiv:1901.05555