Batch Normalization (BN) is a common technique used to speed-up and stabilize training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks (cGANs) for representing class-specific information using conditional Batch Normalization (cBN). In this paper we propose to generalize both BN and cBN using a Whitening and Coloring based batch normalization. We show that our conditional Coloring can represent categorical conditioning information which largely helps the cGAN qualitative results. Moreover, we show that full-feature whitening is important in a general GAN scenario in which the training process is known to be highly unstable. We test our approach on different datasets and using different GAN networks and training protocols, showing a consistent improvement in all the tested frameworks. Our CIFAR-10 conditioned results are higher than all previous works on this dataset.
Cite
@article{arxiv.1806.00420,
title = {Whitening and Coloring batch transform for GANs},
author = {Aliaksandr Siarohin and Enver Sangineto and Nicu Sebe},
journal= {arXiv preprint arXiv:1806.00420},
year = {2019}
}