Question about Pseudo-labels are source domain but not target domain in the code

layumi / Seg-Uncertainty

IJCAI2020 & IJCV2021 :city_sunrise: Unsupervised Scene Adaptation with Memory Regularization in vivo

https://arxiv.org/abs/1912.11164

MIT License

387 stars 51 forks source link

Question about Pseudo-labels are source domain but not target domain in the code #19

Closed jingzhengli closed 3 years ago

jingzhengli commented 3 years ago

Hi, thanks for the nice code~ I have some questions about the pseudo-labels training part of the code,

this is the pseudo labeling loss of the source data as Eq.11 in paper: loss_seg1 = self.update_variance(labels, pred1, pred2), in which the labels come from the source domain.

the target domain does not use the pseudo-labels but the entropy minimization: loss_kl = ( self.kl_loss(self.log_sm(pred_target2) , mean_pred) + self.kl_loss(self.log_sm(pred_target1) , mean_pred))/(nhw)

jingzhengli commented 3 years ago

I saw the #Issue 8 and it solved my confusion