StyDeSty
StyDeSty copied to clipboard
Huage001
PyTorch implementation of paper "StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization" in ICML 2024.
Dear Authors, your work is truly impressive. Would it be possible for you to release the code related to the KITTI and VKITTI datasets?
Congrats on having your work accepted to ICML, that's such an honor. I would like to ask for the code where you combine this method with Meta causal learning [1]...
代码中计算似然损失还有对抗似然的作用是什么，和destylization layer的关系是啥，只是为了降低源域和目标域的分布吗？那用MMD，KL是不是也可以？文中似乎只简单说了一段。其次是destylization layer就是接在后面的几个norm_0 = nn.InstanceNorm2d(96, affine=True)吗？十分感谢！
