Command Palette
Search for a command to run...
Object Detection On Ai Tod
Métriques
AP
AP50
AP75
APm
APs
APt
APvt
Résultats
Résultats de performance de divers modèles sur ce benchmark
| Paper Title | ||||||||
|---|---|---|---|---|---|---|---|---|
| DNTR | 26.2 | 56.7 | 20.2 | 37.0 | 31.0 | 26.4 | 12.8 | A DeNoising FPN With Transformer R-CNN for Tiny Object Detection |
| DetectoRS w/ RFLA | 24.8 | 55.2 | 18.5 | 38.2 | 30.3 | 24.8 | 9.3 | RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection |
| DetectoRS + NWD (ResNet-50-FPN) | 20.8 | 49.3 | 14.3 | 38.3 | 29.6 | 19.7 | 6.4 | A Normalized Gaussian Wasserstein Distance for Tiny Object Detection |
| DetectoRS (ResNet-50-FPN) | 14.8 | 32.8 | 11.4 | 28.0 | 28.3 | 10.8 | 0.0 | DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution |
| M-CenterNet (DLA-34) | 14.5 | 40.7 | 6.4 | 20.4 | 19.4 | 15.0 | 6.1 | Tiny Object Detection in Aerial Images |
| Cascade R-CNN (ResNet-50-FPN) | 13.8 | 30.8 | 10.5 | 26.6 | 25.5 | 10.6 | 0.0 | Cascade R-CNN: Delving into High Quality Object Detection |
| YOLOv5+Inner-IoU | - | - | - | - | - | - | - | Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box |
0 of 7 row(s) selected.