· 2023
Segment Anything
- 9,307citations
- 2023year
Short summary
Meta AI introduces the Segment Anything Model (SAM) and a 1.1 billion mask dataset (SA-1B) for zero-shot image segmentation, achieving performance competitive with or superior to fully supervised methods on various tasks.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduced the Segment Anything (SA) project, including a new task, model (SAM), and dataset (SA-1B).
- Built the largest segmentation dataset to date with over 1 billion masks on 11 million images.
- The Segment Anything Model (SAM) is promptable and designed for zero-shot transfer.
- SAM's zero-shot performance is competitive with or superior to fully supervised results on various tasks.
AI-generated from the title and abstract; the full text is not read.
Abstract
We 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. 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. We recommend reading the full paper at: arxiv.org/abs/2304.02643.
The authors' abstract, as published at the source., 2023 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science