| Paper | Code | Detection AUROC (severity 0) | Detection AUROC (severity 5) | Detection AUROC (severity 10) | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| A framework for benchmarking class-out-of-distribution detection and its application to ImageNet | ✓ Link | 0.9958 | 0.9632 | 0.7748 | ViT-L/32-384 with Max-logit | 2023-02-23 |
| A framework for benchmarking class-out-of-distribution detection and its application to ImageNet | ✓ Link | 0.9955 | 0.9589 | 0.7635 | ViT-L/32-384 with ODIN | 2023-02-23 |
| A framework for benchmarking class-out-of-distribution detection and its application to ImageNet | ✓ Link | 0.9948 | 0.9514 | 0.7332 | ViT-L/32-384 with Entropy | 2023-02-23 |
| A framework for benchmarking class-out-of-distribution detection and its application to ImageNet | ✓ Link | 0.9947 | 0.9478 | 0.712 | ViT-L/32-384 with MC Dropout | 2023-02-23 |
| A framework for benchmarking class-out-of-distribution detection and its application to ImageNet | ✓ Link | 0.9915 | 0.9293 | 0.7 | ViT-L/32-384 with Softmax | 2023-02-23 |