Training generative adversarial networks (GANs) with limited data is challenging because discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the augmentation implicitly introduces undesired invariance to augmentation for the discriminator since it ignores the change of semantics in the label space caused by data transformation, which may limit the representation learning ability of the discriminator and ultimately affect the generative modeling performance of the generator. To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. Particularly, the prediction targets of real data and generated data are required to be distinguished since they are different during training. We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real but not fake data. This formulation connects the learning objective of the generator and the arithmetic$-$harmonic mean divergence under certain assumptions. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures on data-limited CIFAR-10, CIFAR-100, FFHQ, LSUN-Cat, and five low-shot datasets. Experimental results demonstrate significant improvements of our method over SOTA methods in training data-efficient GANs.

翻译：在有限数据条件下训练生成对抗网络（GANs）颇具挑战性，因判别器易陷入过拟合。此前提出的可微数据增强方法虽能提升GAN训练的数据效率，但其隐含地为判别器引入了对增强操作的不良不变性——该方法忽略了数据变换导致标签空间语义变化的问题，这可能会限制判别器的表征学习能力，并最终影响生成器的生成建模性能。为在继承数据增强优势的同时减轻不变性带来的负面影响，我们提出一种新型的增强感知自监督判别器，该判别器能预测增强数据的增强参数。特别地，训练过程中需区分真实数据与生成数据的预测目标，因二者存在差异。我们进一步通过生成可被增强预测的真实而非虚假数据，激励生成器以对抗方式从自监督判别器中学习。该公式在特定假设下将生成器的学习目标与算术-调和平均散度联系起来。我们采用类别条件BigGAN与无条件StyleGAN2架构，在数据受限的CIFAR-10、CIFAR-100、FFHQ、LSUN-Cat及五个低样本数据集上，将所提方法与当前最优方法进行对比。实验结果表明，在训练数据高效GANs领域，我们的方法相较现有最优方法具有显著性能提升。