YOLOX Object Detector Paper Explanation and Custom Training
YOLOX Object Detector Paper Explanation and Custom Training
“Released in July 2021, YOLOX has switched to the anchor free approach which is different from previous YOLO networks. It also introduces advanced detection techniques like Decoupled Head and simOTA label assignment strategy. Moreover, strong data augmentation like MOSAIC and mixUP are incorporated for robust training. YOLOX began with the YOLOv3 SPP model as baseline and performed these modifications one after another…”
Source: learnopencv.com/yolox-object-detector-paper-explanation-and-custom-training/
October 6, 2022
Subscribe
Login
Please login to comment
0 Comments