Anomaly Detection On One Class Cifar 100
Metrics
AUROC
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | AUROC |
|---|---|
| generalad-anomaly-detection-across-domains-by | 98.4 |
| transformaly-two-feature-spaces-are-better | 97.7 |
| learning-and-evaluating-representations-for-1 | 86.5 |
| panda-adapting-pretrained-features-for | 97.3 |
| panda-adapting-pretrained-features-for | 80.1 |
| gan-based-anomaly-detection-in-imbalance | 87.4 |
| deep-unsupervised-image-anomaly-detection-an | 86 |
| deep-anomaly-detection-using-geometric | 78.7 |
| panda-adapting-pretrained-features-for | 62.6 |
| panda-adapting-pretrained-features-for | 67 |
| mean-shifted-contrastive-loss-for-anomaly | 96.5 |
| learning-and-evaluating-representations-for-1 | 84.1 |
| multi-task-transformation-learning-for-robust | 83.95 |
| csi-novelty-detection-via-contrastive | 89.6 |
| panda-adapting-pretrained-features-for | 94.1 |