Support image segmentation in labelling tasks and Visual ML

Antal

I have a couple of use cases where I need to train image (instance) segmentation models (as opposed to predicting bounding boxes in object detection).

I'd love for the ML labelling to support image segmentation approaches. For example using SAM (Segment Anything Model) to pre-segment images which can then be annotated by the user to create image masks.

I really like how Roboflow implements this, for example.

Then, of course, it would also be nice to have image segmentation supported in Visual ML in addition to image classifition and object detection with a couple of models like YOLO, Mask R-CNN, DETIC, OneFormer…)