vikolss / DACS

Code from the paper "DACS: Domain Adaptation via Cross-domain Mixed Sampling"
MIT License
123 stars 19 forks source link

Question about the type of your method #11

Closed super233 closed 3 years ago

super233 commented 3 years ago

Does there exist wamup stage of adversarial training in your method? And is your method only based on self-training? I haven't found the corresponding content in paper so I'm going to ask you.

WilhelmT commented 3 years ago

Hi,

Our method does not rely on adversarial learning.

It is only based on self-training, and a very simple variant where the pseudolabels are simply assigned the class of the highest probability, for every pixel, and from uniformly sampling images as usual.

super233 commented 3 years ago

Thanks for your reply, it's a really an awesome work! 😄