search

ZhenZHAO / iMAS

[CVPR'23] Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentation
https://arxiv.org/abs/2211.11335
36 stars 5 forks source link

Question about the Intensity-based augmentations #1

Closed Hugo-cell111 closed 1 year ago

Hugo-cell111 commented 1 year ago

Hi! I just read the paper of iMAS and find the formula 8. Theoretical speaking, the harder the sample is, the larger its gamma is. So for the hard samples, it is inappropriate to assign large proportion of strong augmentation. For the easy samples, the strong augmentation can be added without too much concern. So I think the correct formula is written as: A_s <- (1 - gamma) A_s + gamma A_w. But in the paper it is A_s <- (1 - gamma) A_w + gamma A_s. So I am confused by it. Could you please explain it? Thanks a lot!

ZhenZHAO commented 1 year ago

Sorry about that. You are right. In my first draft I use the easiness (also in the code), I will correct it later.