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.

Sign up for GitHub

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

Jump to bottom

关于IoUE loss的问题 #4

Open
hzfengfengxia opened this issue Apr 12, 2022 · 5 comments
Open

关于IoUE loss的问题 #4

hzfengfengxia opened this issue Apr 12, 2022 · 5 comments

Comments

@hzfengfengxia
Copy link

你好，我的论文里想引用您文章中IoUE loss的部分，请问可以公开IoUE loss部分的代码让我参考一下吗，非常感谢
@hzfengfengxia
Copy link
Author

image

@hzfengfengxia
Copy link
Author

比如这个公式，请问这个交集和并集代表什么呢？和目标检测中的IoU loss有什么区别呢，谢谢

@fu123456
Copy link
Owner

IoU loss是一个分割领域很常用的损失函数。这里的EIoU实际上是对边界进行约束，即输出结果的边界和gt的边界一致。

@hzfengfengxia
Copy link
Author

好的，非常感谢！

@hzfengfengxia
Copy link
Author

您好，关于A Multi-Task Network for Joint Specular Highlight Detection and Removal这篇文章，还有事情想要请教您。请问方便告知一下文中的BER（Balance error rate）的具体计算公式吗？或者计算BER的代码？

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@fu123456 @hzfengfengxia