Anomaly Detection On Fishyscapes 1
Métriques
AP
FPR95
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | AP | FPR95 |
|---|---|---|
| unmasking-anomalies-in-road-scene | 95.20 | 0.82 |
| evaluating-bayesian-deep-learning-methods-for | 48.7 | 15.5 |
| pixel-wise-energy-biased-abstention-learning | 92.38 | 1.73 |
| densehybrid-hybrid-anomaly-detection-for | 72.3 | 5.5 |
| residual-pattern-learning-for-pixel-wise-out | 95.96 | 0.52 |
| pixel-wise-anomaly-detection-in-complex | 72.59 | 18.75 |
| concurrent-misclassification-and-out-of | 67.8 | 21.58 |
| standardized-max-logits-a-simple-yet | 53.11 | 19.64 |