InstructSAM: Segment Any Instance with Any Instructions
- Published
- Source
- arXiv
- Paper number
- 249
- Field
- Computer Vision
- arXiv ID
- 2605.26102
Key points
- During decoding, the final score head determines whether the query corresponds to a valid target instance, and the segmentation head produces a binary mask.
- For a single target, it identifies the one specific object mentioned in the instruction.
- For multiple targets, it finds all instances that satisfy a complex condition, such as "all wooden chairs."
Paper links
External research summaries. These are not HDATF publications or measured product results.