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/BATS (ResNet-50)

BATS (ResNet-50)

Reported on 7 benchmarks across 1 task · 1 paper · 1 SOTA

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

Computer Vision7 results

  • Out-of-Distribution DetectiononImageNet-1k vs Places
    AUROC· 2022-10-09
    91.83
    best: 93.11 (CMA(ViT-B/16, NegLabel))
    SOTA
    Boosting Out-of-distribution Detection with Typical FeaturesarXiv:2210.04200
  • Out-of-Distribution DetectiononImageNet-1k vs iNaturalist
    AUROC· 2022-10-09
    97.67
    best: 99.62 (CMA(ViT-B/16, NegLabel))
    Boosting Out-of-distribution Detection with Typical FeaturesarXiv:2210.04200
  • Out-of-Distribution DetectiononImageNet-1k vs Textures
    AUROC· 2022-10-09
    92.27
    best: 98.92 (ViM (BiT))
    Boosting Out-of-distribution Detection with Typical FeaturesarXiv:2210.04200
  • Out-of-Distribution DetectiononImageNet-1k vs Textures
    FPR95· 2022-10-09
    38.9
    best: 79.8 (RP+GradNorm)
    Boosting Out-of-distribution Detection with Typical FeaturesarXiv:2210.04200
  • Out-of-Distribution DetectiononImageNet-1k vs Places
    FPR95· 2022-10-09
    34.34
    best: 83.29 (RP+GradNorm)
    Boosting Out-of-distribution Detection with Typical FeaturesarXiv:2210.04200
  • Out-of-Distribution DetectiononImageNet-1k vs Curated OODs (avg.)
    AUROC· 2022-10-09
    94.28
    best: 95.71 (SCALE (ResNet50))
    Boosting Out-of-distribution Detection with Typical FeaturesarXiv:2210.04200
  • Out-of-Distribution DetectiononImageNet-1k vs Curated OODs (avg.)
    FPR95· 2022-10-09
    27.11
    best: 70.12 (RP+GradNorm)
    Boosting Out-of-distribution Detection with Typical FeaturesarXiv:2210.04200