AWhat changed
Introduced a promptable image-segmentation task and model plus the SA-1B dataset of over one billion masks on 11 million images, with reported zero-shot transfer evaluations.
Scientific scope
Introduced a promptable image-segmentation task and model plus the SA-1B dataset of over one billion masks on 11 million images, with reported zero-shot transfer evaluations. Scope limitation: Meta's exact 2023 Segment Anything paper is distinct from later SAM 2/video systems. Zero-shot comparisons and dataset properties are those reported in the paper.
Evidence
The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. Meta's exact 2023 Segment Anything paper is distinct from later SAM 2/video systems. Zero-shot comparisons and dataset properties are those reported in the paper.
Contributors
- The named authors listed in the linked research record · SCIENCE: Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured.
- Kirillov and colleagues: Segment Anything model and SA-1B dataset — original paper
- Kirillov and colleagues: Segment Anything model and SA-1B dataset — company research page
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction