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

Ablation study of auxiliary losses? #43

Open
joeyz0z opened this issue Feb 9, 2023 · 1 comment
Open

Ablation study of auxiliary losses? #43

joeyz0z opened this issue Feb 9, 2023 · 1 comment

Comments

@joeyz0z
Copy link

joeyz0z commented Feb 9, 2023

Hello,
I was wondering about the role of auxiliary losses on each intermediate decoder layer. Can it help to accelerate the model convergence or for other purposes?
Thanks!

@ttengwang
Copy link
Owner

The intermediate loss splits the learning into multiple steps and may ease the learning process. I observed it improves both localization and captioning performance, but I didn't remember it helps convergence.

The design follows the DETR and Deformable-DETR and you may find more analysis in these papers.

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