Segment Anything

TLDR

The Segment Anything project introduces a new task, model, and dataset for image segmentation. An efficient, promptable model was used in a data‑collection loop to create the largest segmentation dataset to date, with over 1 billion masks on 11 million images. The model achieves impressive zero‑shot performance, often matching or surpassing fully supervised results, and the SAM model and SA‑1B dataset are released for research. See the full paper at arxiv.org/abs/2304.02643.

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.