Object Detection On Visdrone Det2019 1
Metrics
AP
AP50
APt
APvt
Results
Performance results of various models on this benchmark
Model Name | AP | AP50 | APt | APvt | Paper Title | Repository |
|---|---|---|---|---|---|---|
| DetectoRS w/ RFLA | 27.4 | 45.3 | 12.9 | 4.5 | RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection | |
| PP-YOLOE-plus | - | 66.7 | - | - | PP-YOLOE: An evolved version of YOLO | |
| Cascade R-CNN + NWD | - | 40.3 | 11.1 | 2.9 | A Normalized Gaussian Wasserstein Distance for Tiny Object Detection | |
| CZ Det. | 33.22 | 58.3 | - | - | Cascaded Zoom-in Detector for High Resolution Aerial Images | |
| DCFL | - | 32.1 | - | - | Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection | |
| LEGNet-S | 32.2 | 55.0 | - | - | LEGNet: Lightweight Edge-Gaussian Driven Network for Low-Quality Remote Sensing Image Object Detection |
0 of 6 row(s) selected.