facebookresearch / facebookresearch/segment-anything
Satellite Imagery(tiny objects) Generalization
- Dominant language
- Jupyter Notebook
- Stars
- 54.9k
- Forks
- 6.4k
- PR merge metrics
- No merged PRs in 30d
Description
Thank you for the incredible work & congratulations!
SAM does not seem to generalize as well on satellite imagery(tiny objects). This was the result of the "**segment everything**" option on the image .
However SAM works better on the **same** image if I manually prompt the model to the object of interest (such as the tiny aircrafts on the LHS corner) that it may have missed in the "segment everything" option.
Couple of more examples with the "segment everything" option:
Any insights on the same would be most helpful !
Contributor guide
Research direction
No specific file, test, or entry point is named. Start by reproducing the reported satellite-imagery behavior with the “segment everything” option, then compare it with manual prompts for the tiny aircraft. Done would require establishing whether the missed objects reflect a model limitation or an actionable defect and documenting the result.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100