swift-n-brutal

After some research, the first problem has been resolved. The default behaviour of ViT.forward() changed in different version of timm. When `global_pool=''`, the backbone returns `x[:, 0]` in timm=v0.5.x, while...

I can get a close result (89.8%) of CDAN+MCC+SDAT on VisDA, but met a strange behaviour. As shown in the image below, the validation accuracy (not the mAP) keeps going...

@Wangzs0228 It is almost sure that the smoothness regularization is beneficial to transferability, robustness, generalization ability, etc. For a specific task, the results may vary. I am not working on...