Pedestrian Detection On Tju Ped Traffic
Métriques
ALL (miss rate)
HO (miss rate)
R (miss rate)
R+HO (miss rate)
RS (miss rate)
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | ALL (miss rate) | HO (miss rate) | R (miss rate) | R+HO (miss rate) | RS (miss rate) | Paper Title | Repository |
|---|---|---|---|---|---|---|---|
| FCOS | 40.02 | 63.73 | 24.35 | 28.86 | 37.40 | FCOS: Fully Convolutional One-Stage Object Detection | |
| FPN | 37.78 | 60.30 | 22.30 | 26.71 | 35.19 | Feature Pyramid Networks for Object Detection | |
| LSFM | - | 56.2 | 18.7 | - | 24.9 | Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving | - |
| EGCL | 35.76 | 60.05 | 19.73 | 24.19 | - | Pedestrian Detection by Exemplar-Guided Contrastive Learning | - |
| RetinaNet | 41.40 | 61.60 | 23.89 | 28.45 | 37.92 | Focal Loss for Dense Object Detection | |
| CrowdDet | 36.94 | 61.22 | 20.82 | 25.28 | - | Detection in Crowded Scenes: One Proposal, Multiple Predictions |
0 of 6 row(s) selected.