Whitening and Coloring transform for GANs.

Batch Normalization (BN) is a common technique used both in discriminative and generative networks in order to speed-up training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks 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 apply our method to conditional and unconditional image generation tasks and we show that replacing the BN feature standardization and scaling with our feature whitening and coloring improves the final qualitative results and the training speed. We test our approach on different datasets and we show a consistent improvement orthogonal to different GAN frameworks. Our CIFAR-10 supervised results are higher than all previous works on this dataset.