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

About the mask update process #5

Open
SvyJ opened this issue Oct 17, 2023 · 1 comment
Open

About the mask update process #5

SvyJ opened this issue Oct 17, 2023 · 1 comment

Comments

@SvyJ
Copy link

SvyJ commented Oct 17, 2023

How are the "background_length=33" and "target_length=3" determined during the mask update process?

@XinyiYing
Copy link
Owner

"background_length" represents the region (background_lengthbackground_length) for label update of each target with a given point label, and is empirically set to 33. Depend on the dataset, you have to make sure that given a point label, a mask of size background_lengthbackground_length can cover the target.
"target_length" are used to eliminate local background clutter. This is, the candidate pixels, which have no intersection with the "target_length*target_length" region of the given point label, are deleted. To ensure precision, we set "target_length" as a small number of 3.

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