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/SCALE (ResNet50)

SCALE (ResNet50)

Reported on 18 benchmarks across 1 task · 1 paper · 3 SOTA

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

Computer Vision18 results

  • Out-of-Distribution DetectiononNear-OOD
    FPR@95· 2023-09-30
    59.76
    SOTA
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononFar-OOD
    FPR@95· 2023-09-30
    16.53
    SOTA
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs Curated OODs (avg.)
    AUROC· 2023-09-30
    95.71
    SOTA
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononNear-OOD
    AUROC· 2023-09-30
    81.36
    best: 84.01 (ISH (ResNet50))
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononNear-OOD
    ID ACC· 2023-09-30
    76.18
    best: 76.74 (ISH (ResNet50))
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs iNaturalist
    AUROC· 2023-09-30
    98.17
    best: 99.62 (CMA(ViT-B/16, NegLabel))
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs iNaturalist
    FPR95· 2023-09-30
    9.5
    best: 68.32 (GEN)
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs iNaturalist
    Latency, ms· 2023-09-30
    11.27
    best: 31 (NNGuide (RegNet))
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs Textures
    AUROC· 2023-09-30
    97.37
    best: 98.92 (ViM (BiT))
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs Textures
    FPR95· 2023-09-30
    12.93
    best: 79.8 (RP+GradNorm)
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs Textures
    Latency, ms· 2023-09-30
    11.27
    best: 31 (NNGuide (RegNet))
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs Places
    AUROC· 2023-09-30
    92.26
    best: 93.11 (CMA(ViT-B/16, NegLabel))
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs Places
    FPR95· 2023-09-30
    34.51
    best: 83.29 (RP+GradNorm)
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononFar-OOD
    AUROC· 2023-09-30
    96.53
    best: 96.79 (ISH (ResNet50))
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononFar-OOD
    ID ACC· 2023-09-30
    76.18
    best: 76.74 (ISH (ResNet50))
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs SUN
    AUROC· 2023-09-30
    95.02
    best: 96.36 (CMA(ViT-B/16, NegLabel))
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs SUN
    FPR95· 2023-09-30
    23.27
    best: 80.94 (DOE)
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227
  • Out-of-Distribution DetectiononImageNet-1k vs Curated OODs (avg.)
    FPR95· 2023-09-30
    20.05
    best: 70.12 (RP+GradNorm)
    Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv:2310.00227