YOLOX: Exceeding YOLO Series in 2021

Benchmark Model Rank Results
2d-object-detection-on-ceymoYOLOX#4mAP: 57.7
object-detection-on-cocoYOLOX-x(Modified CSP v5, 640x640, single-scale)#77box mAP: 51.5
object-detection-on-cocoYOLOX-X (Modified CSP v5)#82box mAP: 51.2AP50: 69.6AP75: 55.7APS: 31.2APM: 56.1APL: 66.1
object-detection-on-cocoYOLOX-Darknet53(Darknet53, 640x640, single-scale)#110box mAP: 48.0
object-detection-on-coco-oYOLOX-X#19Average mAP: 30.3Effective Robustness: 7.26
object-detection-on-coco-oYOLOX-S#29Average mAP: 20.6Effective Robustness: 2.48
object-detection-on-waterscenesYOLOX-M#2mAP@50-95: 57.8
real-time-object-detection-on-cocoYOLOv5-X#51box AP: 50.4FPS (V100, b=1): 62.5