Open canqin001 opened 5 years ago
I find that there is a big gap on u2m. I have tried some tricks, but the performance is still below the paper by 4%-5%. Do you have any ideas to fix the gap?
I think augmentations like affine augmentation used in this repo are helpful. What kinds of tricks have you tried?
I just rotate the target training images to gain some improvements.
I find that there is a big gap on u2m. I have tried some tricks, but the performance is still below the paper by 4%-5%. Do you have any ideas to fix the gap?