HSC

Reported on 3 benchmarks across 3 tasks · 1 paper

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

Methodology1 result

Anomaly DetectiononLeave-One-Class-Out CIFAR-10
AUROC· 2022-05-23
84.8
best: 98.4 (BCE-CLIP)
Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images arXiv:2205.11474

Medical1 result

Semantic SegmentationonPASCAL VOC 2012 test
Mean IoU
74.5
best: 82.9 (SemPLeS (Swin-L))

Audio1 result

10-shot image generationonPASCAL VOC 2012 test
Mean IoU
74.5
best: 82.9 (SemPLeS (Swin-L))