Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

CLQ Detection Head #1

Open
lebron-2016 opened this issue Oct 6, 2023 · 1 comment
Open

CLQ Detection Head #1

lebron-2016 opened this issue Oct 6, 2023 · 1 comment

Comments

@lebron-2016
Copy link

lebron-2016 commented Oct 6, 2023

尊敬的作者您好:

我阅读您的论文过后,有一点理解得不是特别清楚,希望能得到您的解答。

您提出的CLQ方法与先前的Separate Iou Branch方法有哪些区别呢?

image

image

期待您的回复!感谢!!

@dosemeion
Copy link

感觉区别在两个地方:
1、最后的score分数加权方式有差别:CLQ对iou做了指数,然后再与cls相乘;SIB是直接将cls与iou相乘(实际是也是含有指数加权的,可参考https://arxiv.org/abs/1912.05992);
2、一般SIB最后的score分数是不参与训练的,所以推理时会有一个超参,而CLQ是参与训练的(https://github.com/PanffeeReal/CLQ/blob/66132cf2b30f1d9b6b75fbd3b9577af543a825a8/CLQ_head_align_iou_pred.py#L302)。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants