Unsupervised Anomaly Detection On Smap
Métriques
AUC
F1
Precision
Recall
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | AUC | F1 | Precision | Recall |
|---|---|---|---|---|
| multivariate-time-series-anomaly-detection | 98.44 | 88.80 | 79.91 | 99.91 |
| contextflow-generalist-specialist-flow-based | 98.66 | 93.62 | 88.64 | 99.19 |
| unsupervised-deep-anomaly-detection-for-multi | 99.01 | 88.27 | 81.93 | 95.67 |
| graph-neural-network-based-anomaly-detection | 98.64 | 85.18 | 74.80 | 98.91 |
| tranad-deep-transformer-networks-for-anomaly | 99.21 | 89.15 | 80.43 | 99.99 |
| dfm-interpolant-free-dual-flow-matching | 98.6 | 94.1 | 89.7 | 98.9 |
| robust-anomaly-detection-for-multivariate | 98.89 | 87.28 | 81.30 | 94.19 |
| glow-generative-flow-with-invertible-1x1 | 91.55 | 86.05 | 87.40 | 84.93 |