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

咨询 #7

Open
gengyanlei opened this issue Sep 29, 2020 · 3 comments
Open

咨询 #7

gengyanlei opened this issue Sep 29, 2020 · 3 comments

Comments

@gengyanlei
Copy link

您好,我有个问题,您说 狮鹫=狮子+鹰,这个是类别之间差异比较大的可以利用头部类信息;但是像细粒度分类任务中,每类之间都很相似,也存在着严重的长尾分布,这个还能借用头部类的信息么?即:狮鹫=狮子+鹰??

@KaihuaTang
Copy link
Owner

那个例子只是表示tail可以利用head学习出来的feature,并不是真的简单的feature相加。我觉得不管什么任务都只有样本充足的大类才能学习出鲁棒的特征提取器,因为小样本的尾部类不足以学出鲁棒的信息

@KaihuaTang
Copy link
Owner

当然,纯粹一家之见

@gengyanlei
Copy link
Author

好的,谢谢您的回复。

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

2 participants