Segment Anything

Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland +7 more
4/5/2023
cs.CVcs.AIcs.LG

No official code found. Best implementation: facebookresearch/segment-anything (55,039 stars, Apache-2.0, last commit 2024-09-18).

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 https://segment-anything.com to foster research into foundation models for computer vision.

View on arXivView PDF

Code Implementations(1)

facebookresearch/segment-anythingCommunity100%
Apache-2.0

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

55,0396,389Shell, PythonMar 23, 20232 years agoApache-2.0

Similar Papers

SAM 2: Segment Anything in Images and Videos

87% match1 repo20.0k2024

Segment Anything without Supervision

87% match1 repo5022024

Segment Anything Model for Medical Images?

87% match1 repo1722023

Personalize Segment Anything Model with One Shot

86% match1 repo1.7k2023

Segment Anything Model for Medical Image Analysis: an Experimental Study

84% match1 repo1712023

Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarios

83% match2026

Cite this paper

@article{kirillov2023segment,
  title  = {Segment Anything},
  author = {Alexander Kirillov and Eric Mintun and Nikhila Ravi and Hanzi Mao and Chloe Rolland and Laura Gustafson and Tete Xiao and Spencer Whitehead and Alexander C. Berg and Wan-Yen Lo and Piotr Dollár and Ross Girshick},
  year   = {2023},
  eprint = {2304.02643},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2304.02643v1},
  journal = {ICCV 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2304.02643.svg)](https://codeofpaper.com/paper/2304.02643)

Discussion