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

关于DANN中的域鉴别器的域分类准确率 #443

Open
YuGuilliman opened this issue May 23, 2024 · 2 comments
Open

关于DANN中的域鉴别器的域分类准确率 #443

YuGuilliman opened this issue May 23, 2024 · 2 comments

Comments

@YuGuilliman
Copy link

你好,按照DANN的理论思想,域鉴别器在训练得比较好的情况下应该是不能够很好地区分数据是来自源域还是目标域,这意味着域分类的准确率曲线应该是接近50%。但我在DANN上用自己的数据做分类实验的时候,出现了以下的问题:
1.训练过程中域分类准确率达到了100%,但在目标域上的准确率有了较大的提升;
2.源域和目标域分享同一个标签空间,即类0和类1,但即使源域在类0和类1上都达到了100%的准确率,目标域上对类0的准确率只有不到30%,对类1的准确率达到了80+%;
我想问下有没有什么方法解决这样的问题,或者说源域和目标域存在着较大的条件概率分布之类的差异,导致迁移的效果不是很好?
b497b63618df0d69f800177c8439aac
c80a0f455d864ddd339d123b68e84b4

@luhaifeng19947
Copy link

luhaifeng19947 commented May 23, 2024 via email

@wlh-coconut
Copy link

wlh-coconut commented May 23, 2024 via email

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

3 participants