Hello there! I am an engineer at Roboflow. We maintain Autodistill, a framework that enables you to use large foundation models to label data for use in training smaller vision models. I combined Grounding DINO and EdgeSAM to create Grounded EdgeSAM. This combination model allows for zero-shot prompting with Grounding DINO, then EdgeSAM creates masks. You can use this model to label images.
This PR adds a link to the Autodistill module so people can use it to auto-label data.
Hello there! I am an engineer at Roboflow. We maintain Autodistill, a framework that enables you to use large foundation models to label data for use in training smaller vision models. I combined Grounding DINO and EdgeSAM to create Grounded EdgeSAM. This combination model allows for zero-shot prompting with Grounding DINO, then EdgeSAM creates masks. You can use this model to label images.
This PR adds a link to the Autodistill module so people can use it to auto-label data.