Segment Anything
SAM is a promptable AI segmentation system for zero-shot generalization to objects and images.
Source rating 5.0
(90)
0 views
0 saves
Unknown
Verdict
A quick read before you dig into the full page.
- Best if
- SAM is a promptable AI segmentation system for zero-shot generalization to objects and images
- Pick this when
- SAM is a promptable AI segmentation system for zero-shot generalization to objects and images
Overview
Segment Anything (SAM) is a promptable segmentation system developed by Meta AI that offers zero-shot generalization to unfamiliar objects and images without requiring additional training. It allows users to "cut out" any object in any image with a single click. SAM uses a variety of input prompts to perform a wide range of segmentation tasks. The model was trained on millions of images and masks collected through a model-in-the-loop "data engine."
Access & connections
Where you can use Segment Anything.
Platforms
Capabilities
What this tool accepts, produces, and is strongest at.
Highlights
- Promptable segmentation with zero-shot generalization
- Interactive point and box prompts
- Automatic segmentation of entire images
- Integration with other AI systems
- Extensible outputs for use in other applications
FAQ 7
What is Segment Anything | Meta AI?
Segment Anything (SAM) is a promptable segmentation system developed by Meta AI that offers zero-shot generalization to unfamiliar objects and images without requiring additional training. It allows users to "cut out" any object in any image with a single click. SAM uses a variety of input prompts to perform a wide range of segmentation tasks. The model was trained on millions of images and masks collected through a model-in-the-loop "data engine."
How to use Segment Anything | Meta AI?
Users can interact with SAM by providing prompts such as interactive points, boxes, or automatically segmenting everything in an image. The system also supports integration with other systems, such as AR/VR headsets or object detectors, to enable text-to-object segmentation. Users can try the demo on the website.
What type of prompts are supported?
Foreground/background points, bounding box, and mask prompts are supported. Text prompts are explored in our paper but the capability is not released.
What is the structure of the model?
A ViT-H image encoder that runs once per image and outputs an image embedding. A prompt encoder that embeds input prompts such as clicks or boxes. A lightweight transformer based mask decoder that predicts object masks from the image embedding and prompt embeddings.
What data was the model trained on?
The model was trained on our SA-1B dataset. See our dataset viewer.
Does the model produce mask labels?
No, the model predicts object masks only and does not generate labels.
Does the model work on videos?
Currently the model only supports images or individual frames from videos.
Related tools
Recommended
Segment Anything