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.

翻译：在生成对抗网络（GAN）框架内，我们提出通过额外结构建模任务来引导判别器进行自监督表示学习的目标函数。结合施加于网络的高效平滑正则化项，这些目标函数引导判别器学习提取信息性表征，同时保持生成器具备从数据域中采样的能力。具体而言，我们的目标函数鼓励判别器在两个粒度层级上组织特征：在粗粒度层面对齐分布特征（如均值与方差），在细粒度层面将特征聚类为局部簇。在GAN框架内作为特征学习器运作，使我们的自监督系统摆脱了对比表示学习范式中普遍依赖的人工数据增强策略。在CIFAR-10/100及ImageNet子集上的实验表明，为GAN配备我们提出的自监督目标函数，足以产生在表示学习评估指标上与对比学习方法训练的网络相抗衡的判别器。