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

Some questions about the interactive way of the figure presented in the paper. #10

Open

songbingze opened this issue Nov 12, 2024 · 0 comments

songbingze commented Nov 12, 2024

Hi, I am very interested in your work. This is a very amazing method.

There are some issues with the MA. Roads in Fig. 4 of paper.

Segment Anyting's result is that masks repeatedly predict by several click prompts from Mask Decoder, then concat. Or the mask is directly predict by a group of clicks from Mask Decoder.
I also have the same question about CAT-SAM.

Thank you very much for taking the time to review my question. Looking forward to your answer.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment