Giters

imlixinyang / HiSD

Official pytorch implementation of paper "Image-to-image Translation via Hierarchical Style Disentanglement" (CVPR 2021 Oral).

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Data imbalance

ryanqiutu opened this issue · comments

commented

Dear Author, I appreciate your work, but i have some questions about the data imbalance. The face number with glasses is only 1377 as the numbe without glasses is 25622. I want to known the effects of the data imbalance. Thanks~

commented

Thanks for your attention of HiSD.
The imbalance problem can be widely seen in almost all unpaired datasets in I2I area. In most cases, it would be better if you have balanced dataset. Our dataset is directly converted by the label annotation file of CelebA. Since the labels are unbalanced, the numbers of reorganized images are unbalanced, too. However, if you want to focus on this, the results may be improved if you apply some tricks in long-tailed or unbalanced-labels area.