facebookresearch / facebookresearch/segment-anything
Do we need to finetune the models for bounding box based prompt and points-based prompt separately?
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 54.9k
- Forks
- 6.4k
- PR merge metrics
- No merged PRs in 30d
Description
Suppose we have a dataset. I want to finetune a model for interative segmentation so that I can use
it in a auto-annotation platform such as CVAT. I see many of finetuning code for SAM1 algorithm
assume you are using bounding box based prompt. Do I have to use point-based prompt if I
will use points interator in the future?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Review the existing SAM1 fine-tuning code and prompt-handling examples referenced by the issue, then compare bounding-box and point-based interactive segmentation workflows. Determine whether separate fine-tuning is required for CVAT-style point and box prompts; done means providing a supported, evidence-based recommendation.
Written by the indexing model from the issue text.
Assessment
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100