Segment Anything

Image segmentation

Built by Meta AI research, Segment Anything model (SAM) is a promptable segmentation system with zero-shot generalization to unfamiliar objects and images, without the need for additional training.

Intended Use

The Segment Anything Model (SAM) is intended to be used for generating high-quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image. When combined with an object detector, it can perform text to segmentation mask tasks.


The Segment Anything Model (SAM) has been trained on a dataset of 11 million images and 1.1 billion masks and has strong zero-shot performance on a variety of objects.


Chen, Jiaqi and Yang, Zeyu and Zhang, Li. (2023). Semantic Segment Anything. https://github.com/fudan-zvg/Semantic-Segment-Anything