Skip to content
New issue

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

#

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

Already on GitHub? # to your account

Jump to bottom

关于cut_mix_label_adaptive的疑问 #24

Open
xiaotongtongxue opened this issue Mar 15, 2024 · 1 comment
Open

关于cut_mix_label_adaptive的疑问 #24

xiaotongtongxue opened this issue Mar 15, 2024 · 1 comment

Comments

@xiaotongtongxue
Copy link

作者你好，我在我的数据集上运行了你的代码，实验结果很不错。但我有一个问题，就是在cut_mix_label_adaptive函数中，为什么要用到两次cutmix？这个本质不就是将一个更小的labeled区域转移到unlabeled吗？感觉用一次cutmix就行了。有点不太理解，希望作者解答一下，感谢！
@ZhenZHAO
Copy link
Owner

ZhenZHAO commented Mar 15, 2024 •
edited
Loading

您好。这份工作其实就一个观点，增大随机性来产生prediction disagreement。 参考这个，#18 , 这么玩也是为了增大随机性，在citys上这样做会更好。当然了，也是为了弱化labeled数据的影响，因为训练的时候已经在过采样labeled数据了。Hope it helps.

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

No branches or pull requests
2 participants
@ZhenZHAO @xiaotongtongxue