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

Test on large scale dataset? #8

Open
qqqqxxyy opened this issue May 5, 2022 · 1 comment
Open

Test on large scale dataset? #8

qqqqxxyy opened this issue May 5, 2022 · 1 comment

Comments

@qqqqxxyy
Copy link

qqqqxxyy commented May 5, 2022

Dear author,
I have read your paper and very admire your work. The proposal of CCAM is likely to become a new popular technique for self-supervised object localization, just like CAM in WSOL area.
However, I am curious about that have you ever tested your method on large scale dataset, for example ILSVRC ? Since ILSVRC is a popular dataset in WSOL and you compare several WSOL methods in your paper too. Or, do SSOL methods cant handle the large scale dataset for lacking annotations?

@FriedRonaldo
Copy link
Owner

Well, we aimed to solve the "co-localization" problem that assumes the dataset contains the images having the same super-category (e.g. bird), therefore, we did not test our model on the large scale DB.

Because of the purpose, PsyNet might not be proper for ImageNet.

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