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

The question with Fig2 #6

Open
kimjisoo12 opened this issue Mar 24, 2024 · 1 comment
Open

The question with Fig2 #6

kimjisoo12 opened this issue Mar 24, 2024 · 1 comment

Comments

@kimjisoo12
Copy link

Hello, thank you very much for your work. With regard to figure 2 (b) about the calculation method of iou, I think your code should be about judging that the similarity d should be obtained by the difference between features, but this d should contain the category dimension. I would like to ask how to compare the category dimension d with a value variance, whether to average the characteristics of all channels or my understanding is wrong, I hope to get your answer.
image

@Luffy03
Copy link
Owner

Luffy03 commented Mar 25, 2024

Hi, the distance d is also calculated as Eqs. (5) and (6) in our paper.

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