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.

Sign up for GitHub

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

Jump to bottom

adv loss in the paper #2

Open
Danden1 opened this issue Jan 28, 2022 · 0 comments
Open

adv loss in the paper #2

Danden1 opened this issue Jan 28, 2022 · 0 comments

Comments

@Danden1
Copy link

Danden1 commented Jan 28, 2022

In the paper, F is minimize Ladv, D is maximize Ladv. But, I think the opposite is right.

Because, L is loss function not value.
In DANN, D is learned to minimize the domain loss, F is learned to maximize the domain loss using by gradient flip.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@Danden1