facebookresearch / facebookresearch/sam2

Does incomplete labeling affect SAM2 training?

Open
#459 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
19.9k
Forks
2.5k
PR merge metrics
No merged PRs in 30d

Description

I have some images with a lot of instances (>100) for each. I am wondering if I labeled only some of the instances, will the training be affected. I noticed that bounding boxes can be used as prompts in the training. Does this mean only information in a bounding box
is used when predict a single mask? If so, other part of image will not affect the training?

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.