vix.ing · top · new · best · stats · spec

Segment Anything

2023/10/01 by Alexander M. Kirillov, Eric Mintun, Nikhila Ravi +9 · 819 citations
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Visual Attention and Saliency Detection

paper · doi:10.1109/iccv51070.2023.00371

openalex publication_date 2023/10/01 · openalex created_date 2024/01/16 · openalex updated_date 2026/07/31

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.

Citations

Cited by

Related