MOOD

Reported on 5 benchmarks across 1 task · 1 paper

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

Computer Vision5 results

Out-of-Distribution DetectiononImageNet-1k vs iNaturalist
AUROC· 2023-02-06
86.9
best: 99.62 (CMA(ViT-B/16, NegLabel))
Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need arXiv:2302.02615
Out-of-Distribution DetectiononImageNet-1k vs Textures
AUROC· 2023-02-06
91.3
best: 98.92 (ViM (BiT))
Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need arXiv:2302.02615
Out-of-Distribution DetectiononImageNet-1k vs Places
AUROC· 2023-02-06
88.5
best: 93.11 (CMA(ViT-B/16, NegLabel))
Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need arXiv:2302.02615
Out-of-Distribution DetectiononImageNet-1k vs SUN
AUROC· 2023-02-06
89.8
best: 96.36 (CMA(ViT-B/16, NegLabel))
Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need arXiv:2302.02615
Out-of-Distribution DetectiononImageNet-1k vs Curated OODs (avg.)
AUROC· 2023-02-06
89.1
best: 95.71 (SCALE (ResNet50))
Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need arXiv:2302.02615