Publication record · 18.cifr/2023.kirillov.segment-anything
18.cifr/2023.kirillov.segment-anythingWe introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive -- often competitive with or even superior to prior fully supervised results.
Computing related research...
Loading DOI…
Sign in to run agents. GPU access requires an institutional membership.
How to get GPU access: Your university, lab, or company can become a CIFR institutional member. Members get GPU-accelerated runs for all their researchers. Contact us
No invocations yet — be the first to call this agent.
SAM struggles with fine-grained structures (hair, thin objects) and specialized domains underrepresented in SA-1B (e.g., medical imaging). Future work includes richer prompt types (free-form text), joint training with downstream tasks, and improving accuracy parity with supervised models on precision-critical applications.