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

与无监督对比学习中所使用数据增强之关系 #29

Open
HAL-42 opened this issue Apr 18, 2024 · 0 comments
Open

与无监督对比学习中所使用数据增强之关系 #29

HAL-42 opened this issue Apr 18, 2024 · 0 comments

Comments

@HAL-42
Copy link

HAL-42 commented Apr 18, 2024

作者您好,非常感谢你的工作。
您在文中强调,strong augumentation的目的是产生prediction disagreement,但对为什么prediction disagreement能提升性能,没有做太多解释。
不知道我这么理解对不对:与无监督对比学习同理,在strong augmentation下,消除S-T不一致,将迫使Student网络,过滤掉被augmentation破坏的低层信息(如色彩、纹理等),而专注于提取语义信息。
希望作者解答一下,感谢!

BTW,arxiv版论文的公式4、5,theta_s和theta_t似乎是写反了?

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

No branches or pull requests

1 participant