Within the framework of generative adversarial networks (GANs), we propose
objectives that task the discriminator for self-supervised representation
learning via additional structural modeling responsibilities. In combination
with an efficient smoothness regularizer imposed on the network, these
objectives guide the discriminator to learn to extract informative
representations, while maintaining a generator capable of sampling from the
domain. Specifically, our objectives encourage the discriminator to structure
features at two levels of granularity: aligning distribution characteristics,
such as mean and variance, at coarse scales, and grouping features into local
clusters at finer scales. Operating as a feature learner within the GAN
framework frees our self-supervised system from the reliance on hand-crafted
data augmentation schemes that are prevalent across contrastive representation
learning methods. Across CIFAR-10/100 and an ImageNet subset, experiments
demonstrate that equipping GANs with our self-supervised objectives suffices to
produce discriminators which, evaluated in terms of representation learning,
compete with networks trained by contrastive learning approaches.

在生成对抗网络（GAN）框架中，通过额外的结构建模责任，我们提出了使鉴别器能够进行自监督表示学习的目标。结合在网络上施加的高效光滑正则化器，这些目标指导鉴别器学习提取信息性表示，同时保持能够从领域中进行采样的生成器。具体而言，我们的目标鼓励鉴别器在两个粒度级别上对特征进行结构化处理：在粗粒度上对齐分布特征，如均值和方差，在细粒度上将特征分组为本地聚类。作为 GAN 框架中的特征学习器，我们的自监督系统不再依赖于普遍存在于对比表示学习方法中的手工数据增强方案。在 CIFAR-10/100 和 ImageNet 子集上的实验表明，配备我们的自监督目标的 GAN 能够产生在表示学习方面与对比学习方法训练的网络竞争的鉴别器。