Closed weizhao-11 closed 2 years ago
Thx so much for your interest. We obtain consistent and noticeable improvement when alpha is in [2, 3] of alpha-ciou, using YOLOv5s on both PASCAL VOC and COCO.
Is the improvement compared with yolov5s ciou?
Yep, that's right.
Because I didn't see the comparison with ciou in the paper, do I have any doubts, so I want to ask you. Thank you very much for your answer.
No worries.
Yolov5's original loss function is ciou. When a = 3, the accuracy of using a-ciou will decrease by 1.2%. Is it true that a-ciou is not as effective as ciou?