OOD Detection on CIFAR-10 (ID) vs LSUN (OOD) FIX
99.1ROCAUCDeep Clustering for Multi-Class Anomaly Detection
Evaluation results
| Method | Links | |
|---|---|---|
| Deep Clustering for Multi-Class Anomaly DetectionNetwork=ViT, Pre-trained=true2021.12 | 99.1 | |
| Deep Clustering for Multi-Class Anomaly DetectionNetwork=ResNet-152, Pre-trained=true2021.12 | 95.7 | |
| Deep Clustering for Multi-Class Anomaly DetectionNetwork=ResNet-18, Pre-trained=true2021.12 | 94.3 | |
| MSCLNetwork=ResNet-152, Pre-trained=true2021.12 | 92.6 | |
| SCAN FeaturesNetwork=ResNet-18, Pre-trained=false2021.12 | 92.1 | |
| CSINetwork=ResNet-18, Pre-trained=false2021.12 | 90.3 | |
| DN2Network=ResNet-18, Pre-trained=true2021.12 | 88.9 | |
| DN2Network=ResNet-152, Pre-trained=true2021.12 | 86.7 | |
| RotNetwork=ResNet-18, Pre-trained=false2021.12 | 81.6 | |
| GOADNetwork=ResNet-18, Pre-trained=false2021.12 | 78.8 |