Twin Auxiliary Classifiers GAN

Code

• github.com/batmanlab/twin_ac
  OfficialIn paperpytorch★ 0
• github.com/shyam671/Twin_Auxiliary_Classifier_GAN
  pytorch★ 0
• github.com/Ram81/AC-VAEGAN-PyTorch
  pytorch★ 0
• github.com/pranavbudhwant/ACVAEGAN
  pytorch★ 0

Abstract

Conditional generative models enjoy remarkable progress over the past few years. One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN), which generates highly discriminative images by extending the loss function of GAN with an auxiliary classifier. However, the diversity of the generated samples by AC-GAN tends to decrease as the number of classes increases, hence limiting its power on large-scale data. In this paper, we identify the source of the low diversity issue theoretically and propose a practical solution to solve the problem. We show that the auxiliary classifier in AC-GAN imposes perfect separability, which is disadvantageous when the supports of the class distributions have significant overlap. To address the issue, we propose Twin Auxiliary Classifiers Generative Adversarial Net (TAC-GAN) that further benefits from a new player that interacts with other players (the generator and the discriminator) in GAN. Theoretically, we demonstrate that TAC-GAN can effectively minimize the divergence between the generated and real-data distributions. Extensive experimental results show that our TAC-GAN can successfully replicate the true data distributions on simulated data, and significantly improves the diversity of class-conditional image generation on real datasets.

Tasks

Benchmark Results

Reproductions