Supervised Loss for Student

[michaelku1]

Hello @ycliu93, Thanks for your work.

I'd just like to confirm whether the student model actually uses the labelled data as part of training along with the pseudo-labelled data. This is because in the paper the diagram only shows strongly augmented data passed into the student model, but in the code there is a forward pass for the student model that also takes labelled data with both weak and strong augmentations. For your references:

This shows that weakly augmented unlabelled data is for the teacher branch.

This shows that Lsup is from burn-in, and Lunsup is from the supervision of pseudo-labels.

This shows that student model has a forward pass given the labelled data (in which the forward pass is not for the burn-in)

Thanks very much.

[ycliu93]

Thanks for asking. Yes, we input both weak and strong into the student model in the code. And we also tried to only use strong-augmented images, and we got similar results.

[michaelku1]

Thanks, that answered my question.