Despite the potential benefits of data augmentation for mitigating the data insufficiency, traditional augmentation methods primarily rely on the prior intra-domain knowledge. On the other hand, advanced generative adversarial networks (GANs) generate inter-domain samples with limited variety. These previous methods make limited contributions to describing the decision boundaries for binary classification. In this paper, we propose a distance guided GAN (DisGAN) which controls the variation degrees of generated samples in the hyperplane space. Specifically, we instantiate the idea of DisGAN by combining two ways. The first way is vertical distance GAN (VerDisGAN) where the inter-domain generation is conditioned on the vertical distances. The second way is horizontal distance GAN (HorDisGAN) where the intra-domain generation is conditioned on the horizontal distances. Furthermore, VerDisGAN can produce the class-specific regions by mapping the source images to the hyperplane. Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification. The proposed method can apply to different classification architectures and has potential to extend to multi-class classification.

翻译：尽管数据增强在缓解数据不足方面具有潜在优势，传统增强方法主要依赖于先验域内知识。另一方面，先进的生成对抗网络（GANs）能够生成多样性有限的跨域样本。这些先前方法对描述二分类决策边界的贡献有限。本文提出了一种距离引导生成对抗网络（DisGAN），通过在超平面空间中控制生成样本的变化程度。具体而言，我们通过结合两种方式实例化了DisGAN的思想。第一种方式是垂直距离生成对抗网络（VerDisGAN），其中跨域生成以垂直距离为条件。第二种方式是水平距离生成对抗网络（HorDisGAN），其中域内生成以水平距离为条件。此外，VerDisGAN通过将源图像映射到超平面，可以产生类别特定区域。实验结果表明，DisGAN在可解释二分类任务上始终优于基于GAN的增强方法。所提方法可适用于不同分类架构，并具有扩展到多分类的潜力。