Segment Anything

April 05, 2023


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 \href{}{} to foster research into foundation models for computer vision.

Download the Paper


Written by

Alexander Kirillov

Alex Berg

Chloe Rolland

Eric Mintun

Hanzi Mao

Laura Gustafson

Nikhila Ravi

Piotr Dollar

Ross Girshick

Spencer Whitehead

Wan-Yen Lo



Research Topics

Computer Vision

Related Publications

June 04, 2023


Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation

Dahyun Kang, Peter Koniusz, Minsu Cho, Naila Murray

June 04, 2023

May 09, 2023


ImageBind: One Embedding Space To Bind Them All

Rohit Girdhar, Alaa El-Nouby, Zhuang Liu, Mannat Singh, Kalyan Vasudev Alwala, Armand Joulin, Ishan Misra

May 09, 2023

April 20, 2023


SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision

Xubo Liu, Egor Lakomkin, Dino Vougioukas, Pingchuan Ma, Honglie Chen, Ruiming Xie, Morrie Doulaty, Niko Moritz, Jachym Kolar, Stavros Petridis, Maja Pantic, Christian Fuegen

April 20, 2023

April 06, 2023


On the Benefits of 3D Pose and Tracking for Human Action Recognition

Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Christoph Feichtenhofer, Jitendra Malik

April 06, 2023

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.