Semi-supervised novelty detection using ensembles with regularized disagreement
Open paper
Benchmark
Model
Rank
Results
out-of-distribution-detection-on-cifar-10-vs-cifar-100
ERD (ResNet18)
#6
AUROC: 95.1
out-of-distribution-detection-on-cifar-100-vs-cifar-10
ERD (ResNet18)
#7
AUROC: 94.3
Rank counts only results with a code link.