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

Does it work on image segmentation? #2

Closed
sunshuofeng opened this issue Mar 16, 2020 · 2 comments
Closed

Does it work on image segmentation? #2

sunshuofeng opened this issue Mar 16, 2020 · 2 comments

Comments

@sunshuofeng
Copy link

If supermix is used for image segmentation, should we replace KL with an IOU that evaluates x_hat with k inputs and then maximize it?

@alldbi
Copy link
Owner

alldbi commented Mar 16, 2020

Hi,
Yes, it can be used to improve segmentation performance. However, SuperMix should not be changed. You can use a trained classifier and generate mixed images, and then use the mixing masks to produce the corresponding dense segmentation maps. Afterward, the generated images and segments can be used to train the segmentation model.

@sunshuofeng
Copy link
Author

Thanks for your answer! SuperMix is very amazing!

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