Skip to content

Question about using Gaussian filter on anomaly map #31

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

Open
Jasonlee1995 opened this issue Jan 31, 2025 · 1 comment
Open

Question about using Gaussian filter on anomaly map #31

Jasonlee1995 opened this issue Jan 31, 2025 · 1 comment

Comments

@Jasonlee1995
Copy link

I enjoyed ur paper and visit ur repo.

First of all, I'm new in this anomaly detection task.

https://github.com/caoyunkang/AdaCLIP/blob/main/method/trainer.py#L193-L196

What I don't understand is that anomaly map is Gaussian filtered before calculating metrics.

I think controlling this parameter may change the results.
(using Gaussian filter or not, if use then what sigma to use, ...)

Is there specific reason for this? or is it common in this field?

@caoyunkang
Copy link
Owner

Thank you for your interest! In this field, it is common practice to use a Gaussian filter. To ensure fair comparisons, we typically use the same Gaussian filter parameters.

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