Models

What is Segment Anything Model (SAM)?

Segment Anything (SAM) is an image segmentation model developed by Meta Research, capable of doing zero-shot segmentation.

About the model

Here is an overview of the

Segment Anything Model (SAM)

model:

Date of Release Apr 05, 2023
Model Type Instance Segmentation
Architecture
Framework Used
Annotation Format
Stars on GitHub 24000+

Segment Anything, released in April 2023 by Meta Research, is an image segmentation computer vision model trained using a new dataset. The model itself is called Segment Anything Model (SAM). Using SAM, you can generate segmentation masks for all of the objects in an image that the model can find, or masks for objects that meet a provided text prompt.

The dataset on which SAM was trained contains over one billion image masks and 11 million images.

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Check out YOLOv8, defining a new state-of-the-art in computer vision

YOLOv8 is here, setting a new standard for performance in object detection and image segmentation tasks. Roboflow has developed a library of resources to help you get started with YOLOv8, covering guides on how to train YOLOv8, how the model stacks up against v5 and v7, and more.

Learn about YOLOv8

Model Performance

Explore this model on Roboflow

Deploy Segment Anything Model (SAM) to production

Roboflow offers a range of SDKs with which you can deploy your model to production.

Segment Anything Model (SAM) Annotation Format

Segment Anything Model (SAM)

uses the

uses the

annotation format. If your annotation is in a different format, you can use Roboflow's annotation conversion tools to get your data into the right format.

Convert data between formats

Label data automatically with Segment Anything Model (SAM)

You can automatically label a dataset using

Segment Anything Model (SAM)

with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use

Segment Anything Model (SAM)

to train a computer vision model.

No items found.

Compare to related models

Curious about how this model compares to others? Check out our model comparisons.

We have not created any model comparisons yet for this model.

Deploy a computer vision model today

Join 100k developers curating high quality datasets and deploying better models with Roboflow.

Get started
MANAGING over 100 million images for companies of all sizes

Join over 250,000 developers managing computer vision data on Roboflow.

VentureBeatTechCrunchInteresting EngineeringInternational Business TimesU.S. News & World ReportYahoo Finance