facebookresearch / facebookresearch/segment-anything
Reproducing segmentation results shown in the demo
- Dominant language
- Jupyter Notebook
- Stars
- 54.9k
- Forks
- 6.4k
- PR merge metrics
- No merged PRs in 30d
Description
Here are the segmentation results obtained by using the auto-segmentation button provided on the official website (https://segment-anything.com/demo)
These are the segmentation results generated using the released code. Specifically, I used the ViT-H model with all hyperparameters set to their default values.
The results generated by the released code are obviously poorer than those obtained from the official website. Why is this the case, and what model is used in the website version?
Contributor guide
Research direction
Start by comparing the official website demo with the released code using the ViT-H model and its default hyperparameters. Determine why the segmentation results differ and identify which model the website version uses; done means providing a clear explanation of the discrepancy.
Written by the indexing model from the issue text.
Assessment
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100