We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
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?
期待您的回复!感谢!!
The text was updated successfully, but these errors were encountered:
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)。
Sorry, something went wrong.
No branches or pull requests
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?
期待您的回复!感谢!!
The text was updated successfully, but these errors were encountered: