You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Jul 22, 2024. It is now read-only.
Hi, thanks for your excellent work.
I'm wondering the effectiveness of the fully connected layer. In the paper, the fully connected layer produces a support vector for every training input. Since there is no ablation study, I want to know what will happen if we just employ the outputs from the feature extractor to calculate prototypes?
The text was updated successfully, but these errors were encountered:
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Hi, thanks for your excellent work.
I'm wondering the effectiveness of the fully connected layer. In the paper, the fully connected layer produces a support vector for every training input. Since there is no ablation study, I want to know what will happen if we just employ the outputs from the feature extractor to calculate prototypes?
The text was updated successfully, but these errors were encountered: