OOD Detection on CIFAR-10 vs CIFAR-100
0.967ROCAUCDeep Clustering for Multi-Class Anomaly Detection
Evaluation results
| Method | Links | |
|---|---|---|
| Deep Clustering for Multi-Class Anomaly DetectionNetwork=ViT, Pre-trained=true2021.12 | 0.967 | |
| Deep Clustering for Multi-Class Anomaly DetectionNetwork=ResNet-152, Pre-trained=true2021.12 | 0.933 | |
| Deep Clustering for Multi-Class Anomaly DetectionNetwork=ResNet-18, Pre-trained=true2021.12 | 0.908 | |
| SCAN FeaturesNetwork=ResNet-18, Pre-trained=false2021.12 | 0.902 | |
| MSCLNetwork=ResNet-152, Pre-trained=true2021.12 | 0.9 | |
| SSDNetwork=ResNet-18, Pre-trained=false2021.12 | 0.896 | |
| CSINetwork=ResNet-18, Pre-trained=false2021.12 | 0.892 | |
| DN2Network=ResNet-152, Pre-trained=true2021.12 | 0.865 | |
| DN2Network=ResNet-18, Pre-trained=true2021.12 | 0.833 | |
| RotNetwork=ResNet-18, Pre-trained=false2021.12 | 0.823 | |
| GOADNetwork=ResNet-18, Pre-trained=false2021.12 | 0.772 | |
| Input ComplexityNetwork=Glow, Pre-trained=false2021.12 | 0.736 | |
| LikelihoodNetwork=Glow, Pre-trained=false2021.12 | 0.582 |