Unsupervised Anomaly Detection On Smap
Métriques
AUC
F1
Precision
Recall
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | AUC | F1 | Precision | Recall | Paper Title | Repository |
|---|---|---|---|---|---|---|
| MTAD-GAT | 98.44 | 88.80 | 79.91 | 99.91 | Multivariate Time-series Anomaly Detection via Graph Attention Network | |
| ContextFlow++ (Glow-based) | 98.66 | 93.62 | 88.64 | 99.19 | ContextFlow++: Generalist-Specialist Flow-based Generative Models with Mixed-Variable Context Encoding | |
| CAE-M | 99.01 | 88.27 | 81.93 | 95.67 | Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals | - |
| GDN | 98.64 | 85.18 | 74.80 | 98.91 | Graph Neural Network-Based Anomaly Detection in Multivariate Time Series | |
| TranAd | 99.21 | 89.15 | 80.43 | 99.99 | TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data | |
| DFM (flow matching) | 98.6 | 94.1 | 89.7 | 98.9 | DFM: Interpolant-free Dual Flow Matching | - |
| OmniAnomaly | 98.89 | 87.28 | 81.30 | 94.19 | Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network | |
| Glow | 91.55 | 86.05 | 87.40 | 84.93 | Glow: Generative Flow with Invertible 1x1 Convolutions |
0 of 8 row(s) selected.