Conditional GANs with Auxiliary Discriminative Classifier

21 Jul 2021  ·  Liang Hou, Qi Cao, HuaWei Shen, Siyuan Pan, Xiaoshuang Li, Xueqi Cheng ·

Conditional generative models aim to learn the underlying joint distribution of data and labels to achieve conditional data generation. Among them, the auxiliary classifier generative adversarial network (AC-GAN) has been widely used, but suffers from the problem of low intra-class diversity of the generated samples. The fundamental reason pointed out in this paper is that the classifier of AC-GAN is generator-agnostic, which therefore cannot provide informative guidance for the generator to approach the joint distribution, resulting in a minimization of the conditional entropy that decreases the intra-class diversity. Motivated by this understanding, we propose a novel conditional GAN with an auxiliary discriminative classifier (ADC-GAN) to resolve the above problem. Specifically, the proposed auxiliary discriminative classifier becomes generator-aware by recognizing the class-labels of the real data and the generated data discriminatively. Our theoretical analysis reveals that the generator can faithfully learn the joint distribution even without the original discriminator, making the proposed ADC-GAN robust to the value of the coefficient hyperparameter and the selection of the GAN loss, and stable during training. Extensive experimental results on synthetic and real-world datasets demonstrate the superiority of ADC-GAN in conditional generative modeling compared to state-of-the-art classifier-based and projection-based conditional GANs.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Conditional Image Generation CIFAR-10 ADC-GAN FID 5.66 # 6
Intra-FID 40.45 # 1
Conditional Image Generation CIFAR-100 ADC-GAN FID 8.12 # 3
Intra-FID 49.24 # 1
Conditional Image Generation ImageNet 128x128 ADC-GAN FID 8.02 # 11
Inception score 108.10 # 10
Conditional Image Generation Tiny ImageNet ADC-GAN FID 19.02 # 1
Intra-FID 63.05 # 1