Triple Generative Adversarial Nets

TL;DR

Triple-GAN introduces a three-player framework to improve semi-supervised learning and image generation by separately optimizing the generator, discriminator, and classifier, leading to better class control and state-of-the-art results.

Contribution

It proposes a novel three-player GAN model that addresses limitations of previous two-player models by decoupling roles and improving class semantics control.

Findings

Achieves state-of-the-art classification accuracy among deep generative models.

Effectively disentangles class and style, enabling smooth interpolation in latent space.

Demonstrates improved semi-supervised learning performance on various datasets.

Abstract

Generative Adversarial Nets (GANs) have shown promise in image generation and semi-supervised learning (SSL). However, existing GANs in SSL have two problems: (1) the generator and the discriminator (i.e. the classifier) may not be optimal at the same time; and (2) the generator cannot control the semantics of the generated samples. The problems essentially arise from the two-player formulation, where a single discriminator shares incompatible roles of identifying fake samples and predicting labels and it only estimates the data without considering the labels. To address the problems, we present triple generative adversarial net (Triple-GAN), which consists of three players---a generator, a discriminator and a classifier. The generator and the classifier characterize the conditional distributions between images and labels, and the discriminator solely focuses on identifying fake image-label pairs. We design compatible utilities to ensure that the distributions characterized by the classifier and the generator both converge to the data distribution. Our results on various datasets demonstrate that Triple-GAN as a unified model can simultaneously (1) achieve the state-of-the-art classification results among deep generative models, and (2) disentangle the classes and styles of the input and transfer smoothly in the data space via interpolation in the latent space class-conditionally.