Skip to main content
PaperComputer Visionv1.0

Segment Anything

by Meta AI · open-source · Last verified 2026-03-17

Introduced the Segment Anything Model (SAM) and the SA-1B dataset of 1 billion masks on 11 million images. SAM is a promptable segmentation foundation model that generalizes to new image distributions and tasks without additional training, enabling a new paradigm of interactive segmentation.

https://arxiv.org/abs/2304.02643
B+
B+Good
Adoption: A+Quality: A+Freshness: ACitations: A+Engagement: F

Specifications

License
Apache 2.0
Pricing
open-source
Capabilities
image-segmentation, zero-shot-segmentation, interactive-segmentation
Integrations
huggingface, roboflow
Use Cases
object-segmentation, image-annotation, medical-imaging, robotics
API Available
No
Tags
segmentation, foundation-model, promptable, sam, zero-shot
Added
2026-03-17
Completeness
100%

Index Score

79.2
Adoption
93
Quality
95
Freshness
82
Citations
92
Engagement
0

Put AI to work for your business

Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.

Explore the full AI ecosystem on Agents as a Service