Research Area:  Machine Learning
We propose a unified game-theoretical framework to perform classification and conditional image generation given limited supervision. It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN). The generator and the classifier characterize the conditional distributions between images and labels to perform conditional generation and classification, respectively. The discriminator solely focuses on identifying fake image-label pairs. Theoretically, the three-player formulation guarantees consistency. Namely, under a nonparametric assumption, the unique equilibrium of the game is that the distributions characterized by the generator and the classifier converge to the data distribution. As a byproduct of the three-player formulation, Triple-GAN is flexible to incorporate different semi-supervised classifiers and GAN architectures. We evaluate Triple-GAN in two challenging settings, namely, semi-supervised learning and the extreme low data regime. In both settings, Triple-GAN can achieve excellent classification results and generate meaningful samples in a specific class simultaneously. In particular, using a commonly adopted 13-layer CNN classifier, Triple-GAN outperforms extensive semi-supervised learning methods substantially on several benchmarks no matter data augmentation is applied or not.
Keywords:  
Author(s) Name:  Chongxuan Li; Kun Xu; Jun Zhu; Jiashuo Liu; Bo Zhang
Journal name:  IEEE Transactions on Pattern Analysis and Machine Intelligence
Conferrence name:  
Publisher name:  IEEE
DOI:  10.1109/TPAMI.2021.3127558
Volume Information:  Page(s): 1 - 1
Paper Link:   https://ieeexplore.ieee.org/abstract/document/9613799