JDAI-CV / FADA

(ECCV 2020) Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Question

zang5xixi opened this issue · comments

I recently read this paper, and there is a problem I didn't figure out. How to calculate μi in the CCD formula? Is it to use source samples or source samples and target samples?

Hi @zang5xixi,
Thanks for your interest. In the paper we use both source and target samples to compute a global class center μi.

I recently read this paper, and there is a problem I didn't figure out. How to calculate μi in the CCD formula? Is it to use source samples or source samples and target samples?

Hi @zang5xixi,
Thanks for your interest. In the paper we use both source and target samples to compute a global class center μi.

thank you for your reply. I would also like to ask, do you still keep the CCD of AdaptSegNet and CLAN in each category?

Hi @zang5xixi, I follow the same way to compute CCD for AdaptSegNet and CLAN using their provided pre-trained model on GTA5->Cityscapes task.

Hi @zang5xixi, I follow the same way to compute CCD for AdaptSegNet and CLAN using their provided pre-trained model on GTA5->Cityscapes task.

Thank you very much~