Conditional generative models aim to learn the underlying joint distribution of data and labels, and thus realize conditional generation. Among them, auxiliary classifier generative adversarial networks (AC-GAN) have been widely used, but suffer from the issue of low intra-class diversity on generated samples. In this paper, we point out that the fundamental reason is that the classifier of AC-GAN is generator-agnostic, and thus cannot provide informative guidance to the generator to approximate the target joint distribution, leading to a minimization of conditional entropy that decreases the intra-class diversity. Based on this finding, we propose novel cGANs with auxiliary discriminative classifier (ADC-GAN) to address the issue of AC-GAN. Specifically, the auxiliary discriminative classifier becomes generator-aware by distinguishing between the real and fake data while recognizing their labels. We then optimize the generator based on the auxiliary classifier along with the original discriminator to match the joint and marginal distributions of the generated samples with those of the real samples. We provide theoretical analysis and empirical evidence on synthetic and real-world datasets to demonstrate the superiority of the proposed ADC-GAN compared to competitive cGANs.
翻译:在本文中,我们指出,基本原因是AC-GAN的分类者是生成者-不可知性,因此无法为生成者提供信息指导以接近目标的联合分布,从而导致减少有条件的诱变,从而降低阶级内部多样性。根据这一发现,我们提议使用带有辅助性歧视分类者(ADC-GAN)的新型cGAN(ADC-GAN),以解决AC-GAN问题。具体地说,辅助性歧视分类者通过区分真实和假数据,同时承认其标签,成为生成者-GAN。然后,我们优化基于辅助分类器的发电机,同时优化原始分析器,使生成的样品与真实样本的联合和边际分布相匹配。我们提供了合成和真实的合成和真实世界数据集的理论分析和经验证据,以证明拟议的AAN-G的竞争力。