World Model · podcast knowledge graph

Segment Anything 2 product

3 mentions · across 1 show · also seen as book

Segment Anything is a series of open-source computer vision foundation models developed by Meta AI for image and video segmentation. The project was introduced in April 2023 with the Segment Anything Model (SAM), a promptable segmentation model trained on the SA-1B dataset of over 1.1 billion masks, and has since been extended by SAM 2 (2024), which unified image and video segmentation, and SAM 3 (2025), which added segmentation from natural-language concept prompts. The models are released under the Apache 2.0 license and have been widely adopted in research and industry, including medical imaging, earth observation, robotics, and content editing tools.

https://github.com/facebookresearch/segment-anything-2

Relationship map

Connections 2

mentioned 1

references 1

Heard in

Mentioned in episodes

  • 2024-08-07 · Latent Space: The AI Engineer Podcast · via mentioned · 0.90
    Link in episode "Segment Anything 2: Demo-first Model Development": https://github.com/facebookresearch/segment-anything-2
  • 2024-08-07 · Latent Space: The AI Engineer Podcast · via references · 0.77
    Link in episode "Segment Anything 2: Demo-first Model Development": https://github.com/facebookresearch/segment-anything-2
All extracted evidence for this entity (3)
description:link Segment Anything 2: Demo-first Model Development
Link in episode "Segment Anything 2: Demo-first Model Development": https://github.com/facebookresearch/segment-anything-2
description:link Segment Anything 2: Demo-first Model Development
Link in episode "Segment Anything 2: Demo-first Model Development": https://github.com/facebookresearch/segment-anything-2
description:book-authored Segment Anything 2: Demo-first Model Development
author of Segment Anything 2