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

Attention over similarity matrix (AOSM) question #8

Open
reddyav1 opened this issue Oct 21, 2024 · 0 comments
Open

Attention over similarity matrix (AOSM) question #8

reddyav1 opened this issue Oct 21, 2024 · 0 comments

Comments

@reddyav1
Copy link

I see here that X-CLIP uses learnable weight matrices to compute the final scores from the similarity vectors/matrices. However, I am having trouble reconciling this with the equations in Section 3.3 of the paper, which seem to show just a softmax-weighted summation with no learnable parameters.

I'm not sure what I'm missing here. Would you mind clarifying this for me?

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

1 participant