Feature Statistics Mixing Regularization for Generative Adversarial Networks. (arXiv:2112.04120v2 [cs.CV] UPDATED)

In generative adversarial networks, improving discriminators is one of the
key components for generation performance. As image classifiers are biased
toward texture and debiasing improves accuracy, we investigate 1) if the
discriminators are biased, and 2) if debiasing the discriminators will improve
generation performance. Indeed, we find empirical evidence that the
discriminators are sensitive to the style (e.g., texture and color) of images.
As a remedy, we propose feature statistics mixing regularization (FSMR) that
encourages the discriminator's prediction to be …

arxiv cv generative adversarial networks networks regularization statistics