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

What is the effect of replacing transformer with swin transformer? #26

Open
wanglibo0626 opened this issue Aug 17, 2021 · 2 comments
Open

Comments

@wanglibo0626
Copy link

Hi,

Thanks for your good job!What is the effect of replacing transformer with swin transformer?

Looking forward to your reply~

@MasterBin-IIAU
Copy link
Collaborator

Hi, thanks for your appreciation in our work.
I think that replacing the original transformer with Swin-T may reduce some computational complexity but will not bring performance gain, because the shifted-window attention is an approximation to the full attention.
In fact, instead we have tried replacing ResNet with Swin-T as the backbone, this does bring much better performance.

@Chenlulu1993
Copy link

Hi, when you used Swin-T as the backbone, which layers of Swin-T were used in your work? Could you send me the STARK code using Swin-T as the backbone? Thank you very much!

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

3 participants