jevenzh / triple-gan

Triple-GAN: a unified framework for classification and class-conditional generation in semi-supervised learing

Triple Generative Adversarial Nets (Triple-GAN)

Chongxuan Li, Kun Xu, Jun Zhu and Bo Zhang

Code for reproducing most of the results in the paper. Triple-GAN: a unified GAN model for classification and class-conditional generation in semi-supervised learning.

Warning: the code is still under development.

Some libs we used in our experiments

Python Numpy Scipy Theano Lasagne Parmesan

Thank the authors of these libs. We also thank the authors of Improved-GAN and Temporal Ensemble for providing their code. Our code is widely adapted from their repositories.

Results

Triple-GAN can achieve excellent classification results on MNIST, SVHN and CIFAR10 datasets, see the paper for a comparison with previous state-of-the-art. See generated images as follows:

Comparing Triple-GAN (right) with GAN trained with feature matching (left)

Generating images in four specific classes (airplane, automobile, bird, hourse)

Disentangling styles from classes (left: data, right: Triple-GAN)

Class-conditional linear interpolation on latent space