HackerPapers

arXiv:2304.02643cs.CV

Segment Anything

Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollár, Ross Girshick

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.

arXiv comments
Project web-page: https://segment-anything.com
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition cs.AIArtificial Intelligence cs.LGMachine Learning

On Hacker News

Linked by 2 identifiable commenters in 2 comments across 2 threads, from Apr 2023 to May 2024.

Comments linking this paper, per year.

Discussed in comments2 threads

  1. Convolutional Neural Networks for Visual Recognition 1 comment

    • ViTs also have proven to be more effective for zero-shot generalization tasks due to their ability to capture global context and relationships in the input data, which CNNs struggle with. https://arxiv.org/abs/2304.02643

      abrichrView on HNParent context

  2. Segment Anything Model (SAM) can "cut out" any object in an image 1 comment

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.