Still vastly underused in image to image to this day and I don't understand why: Unets and self-attention. I keep seeing papers come out that have obvious problems that could be solved using these two simple things!
-
@citnaj is there a good example of a paper that uses both? I'm curious
Not a paper but DeOldify of course :) . I'm not sure what to recommend to you otherwise but there's some work done in biomedical image segmentation that I've seen.
