Megvii-BaseDetection / YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How are false positives reduced in YOLOX?

adityadmore2000 opened this issue · comments

@FateScript I came across this issue of mispredictions being made in YOLOX. When images of such mispredictions are added while training, the mispredictions get reduced. Any idea how this works internally?