facebookresearch / facebookresearch/segment-anything

Do we need to finetune the models for bounding box based prompt and points-based prompt separately?

Open
#794 0 comments 0 reactions 0 assignees View on GitHub

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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.