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

Mismatch between images and annotations in Cat-16 #26

Open
yangyu12 opened this issue Sep 8, 2021 · 2 comments
Open

Mismatch between images and annotations in Cat-16 #26

yangyu12 opened this issue Sep 8, 2021 · 2 comments

Comments

@yangyu12
Copy link

yangyu12 commented Sep 8, 2021

Hi,
I have found that in Cat-16 some annotations do not match the images. Examples are as follows

Index Provided in Google drive Generated from StyleGAN Annotation shown in supplementary material
image_23 image image image image
image_26 image image image image

Clearly, neither the images provided in Google drive nor the images generated from StyleGAN could match the annotations, but only the images shown in the supplementary material can match the annotations. I think this mismatch is quite obvious as an additional leg is annotated in image_23 while one leg is missing in annotations of image_26. I tend to believe that the released images and latents are wrongly taken. Is it possible to fix this issue?

@arieling
Copy link
Collaborator

arieling commented Sep 8, 2021

Hi, Thank you for pointing this out. There is a discrepancy caused by the noise channel and we are looking into it.
At the same time, please ignore those two annotations.

@yangyu12
Copy link
Author

yangyu12 commented Sep 9, 2021

Hi, I do not think it is caused by the noise channel. Look at the first two columns which show that the images provided in Google drive can be recovered with StyleGAN given the provided latents. Moreover, Car and Face do not have this issue.

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