Due to the outstanding capability for data generation, Generative Adversarial Networks (GANs) have attracted considerable attention in unsupervised learning. However, training GANs is difficult, since the training distribution is dynamic for the discriminator, leading to unstable image representation. In this paper, we address the problem of training GANs from a novel perspective, \emph{i.e.,} robust image classification. Motivated by studies on robust image representation, we propose a simple yet effective module, namely AdaptiveMix, for GANs, which shrinks the regions of training data in the image representation space of the discriminator. Considering it is intractable to directly bound feature space, we propose to construct hard samples and narrow down the feature distance between hard and easy samples. The hard samples are constructed by mixing a pair of training images. We evaluate the effectiveness of our AdaptiveMix with widely-used and state-of-the-art GAN architectures. The evaluation results demonstrate that our AdaptiveMix can facilitate the training of GANs and effectively improve the image quality of generated samples. We also show that our AdaptiveMix can be further applied to image classification and Out-Of-Distribution (OOD) detection tasks, by equipping it with state-of-the-art methods. Extensive experiments on seven publicly available datasets show that our method effectively boosts the performance of baselines. The code is publicly available at https://github.com/WentianZhang-ML/AdaptiveMix.

翻译：鉴于生成对抗网络（GANs）在数据生成方面的卓越能力，其已在无监督学习领域引起广泛关注。然而，由于判别器的训练分布具有动态性，导致图像表征不稳定，使得GAN训练变得困难。本文从稳健图像分类这一新颖视角出发，探讨GAN训练问题。受稳健图像表征研究的启发，我们提出一种名为AdaptiveMix的简易高效模块，该模块能收缩判别器图像表征空间中训练数据的分布区域。考虑到直接约束特征空间难以实现，我们提出构建困难样本并缩小困难样本与简单样本之间的特征距离。困难样本通过混合一对训练图像构建而成。我们采用广泛使用且最先进的GAN架构验证了AdaptiveMix的有效性。评估结果表明，AdaptiveMix能够促进GAN训练，并有效提升生成样本的图像质量。我们还证明，通过将AdaptiveMix与最先进方法相结合，可进一步将其应用于图像分类和分布外（OOD）检测任务。在七个公开数据集上的大量实验表明，我们的方法有效提升了基准模型的性能。代码已开源发布在https://github.com/WentianZhang-ML/AdaptiveMix。