Segment Anything

We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images at segment-anything.com to foster research into foundation models for computer vision.

⚡ This is an original paraphrased summary — not copied from the abstract. Full paper available at the source link below.

• 1 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.
• 2 The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks.
• 3 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.

This research advances how AI systems learn, reason, and solve problems — with direct implications for automation and scientific discovery.

This summary is based on publicly available metadata and abstract. For the full research paper, visit the original source: