I noticed that you also applied this method to image segmentation in the appendix of your paper. I would like to know how you made it work in image segmentation. What were your inputs, and how were the prompts given or automatically generated? Thank you for your reply.
I noticed that you also applied this method to image segmentation in the appendix of your paper. I would like to know how you made it work in image segmentation. What were your inputs, and how were the prompts given or automatically generated? Thank you for your reply.