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 invariant to the styles of input images. Specifically, we generate a mixed feature of an original and a reference image in the discriminator's feature space and we apply regularization so that the prediction for the mixed feature is consistent with the prediction for the original image. We conduct extensive experiments to demonstrate that our regularization leads to reduced sensitivity to style and consistently improves the performance of various GAN architectures on nine datasets. In addition, adding FSMR to recently-proposed augmentation-based GAN methods further improves image quality. Code will be publicly available online for the research community.

翻译：在基因对抗网络中,改善歧视者是生成性能的关键组成部分之一。由于图像分类者偏向于质地和贬低性能提高准确性,我们调查:(1)如果歧视者有偏向,(1)如果歧视者偏向,(2)如果贬低歧视者会提高生成性能。事实上,我们发现经验证据表明,歧视者对图像的风格(例如,质地和颜色)很敏感。作为一种补救措施,我们建议将特征统计混合在一起,使规范化(FSMR)鼓励歧视者的预测与输入性图像的风格不同。具体地说,我们在歧视者特征空间中产生原始和参考图像的混合特征,我们采用规范化,以使混合特征的预测与原始图像的预测相一致。我们进行了广泛的实验,以证明我们的规范化会降低对风格的敏感度,并不断改善九套数据集上的各种GAN结构的性能。此外,在近期推出的基于增强性GAN方法中增加FSMR的特性,从而进一步提高图像质量。我们将在网上向研究界公开提供守则。