Open eternal-f1ame opened 1 year ago
SAM is originally an instance segmentation model. I suggest that all points of the whole image be used as prompts, and the label can use the instance segmentation label of each car. finetune-anything does not yet support instance segmentation tasks, it will be updated later, thank you for your attention
Can I finetune the model using multiple bounding boxes for the same Image (eg. in case of KITTI Dataset if I want to finetune the model to segment cars from background and there are multiple instances of cars in the background) Is there a way I can provide the bounding boxes for all cars in that frame as my prompt or should I iteratively give the bounding box and segmentation of every single instance of a car.