ERD (ResNet18)

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision3 results

Out-of-Distribution DetectiononCIFAR-10 vs CIFAR-10.1
AUROC· uses extra data· 2020-12-10
91.4
SOTA
Semi-supervised novelty detection using ensembles with regularized disagreement arXiv:2012.05825
Out-of-Distribution DetectiononCIFAR-100 vs CIFAR-10
AUROC· uses extra data· 2020-12-10
94.3
best: 100 (DHM)
SOTA
Semi-supervised novelty detection using ensembles with regularized disagreement arXiv:2012.05825
Out-of-Distribution DetectiononCIFAR-10 vs CIFAR-100
AUROC· uses extra data· 2020-12-10
95.1
best: 100 (DHM)
Semi-supervised novelty detection using ensembles with regularized disagreement arXiv:2012.05825