Training generative adversarial networks (GANs) with limited data is challenging because the 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 and 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（GAN）面临判别器易过拟合的挑战。现有可微分增强技术虽能提升GAN训练的数据效率，但该方法隐式引入了判别器对数据增强的不变性——由于忽略数据变换引起的标签空间语义变化，可能限制判别器的表征学习能力，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缓解不变性带来的负面影响，我们提出一种新颖的感知增强自监督判别器，通过预测增强数据的增强参数实现优化。特别地，真实数据与生成数据的预测目标在训练过程中存在差异，需加以区分。我们进一步通过生成可预测增强参数的真实而非伪造数据，引导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建立了生成器学习目标与算术-调和平均散度的联系。我们基于类条件BigGAN和无条件StyleGAN2架构，在数据受限的CIFAR-10、CIFAR-100、FFHQ、LSUN-Cat及五个小样本数据集上，将所提方法与当前最优（SOTA）方法进行对比。实验结果表明，在训练数据高效GAN时，本方法相较SOTA方法具有显著性能提升。