Real Time Object Detection On Pascal Voc 2007
Métriques
FPS
MAP
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | FPS | MAP | Paper Title | Repository |
|---|---|---|---|---|
| BlitzNet512 (s4) | 24 | 79.1% | BlitzNet: A Real-Time Deep Network for Scene Understanding | |
| R-FCN | 9 | 80.5% | R-FCN: Object Detection via Region-based Fully Convolutional Networks | |
| BlitzNet512 (s8) | 19.5 | 81.5% | BlitzNet: A Real-Time Deep Network for Scene Understanding | |
| YOLO | 46.0 | 63.4% | You Only Look Once: Unified, Real-Time Object Detection |
0 of 4 row(s) selected.