Poster
Triangle Generative Adversarial Networks
Zhe Gan · Liqun Chen · Weiyao Wang · Yuchen Pu · Yizhe Zhang · Hao Liu · Chunyuan Li · Lawrence Carin

Wed Dec 6th 06:30 -- 10:30 PM @ Pacific Ballroom #116 #None
A Triangle Generative Adversarial Network ($\Delta$-GAN) is developed for semi-supervised cross-domain joint distribution matching, where the training data consists of samples from each domain, and supervision of domain correspondence is provided by only a few paired samples. $\Delta$-GAN consists of four neural networks, two generators and two discriminators. The generators are designed to learn the two-way conditional distributions between the two domains, while the discriminators implicitly define a ternary discriminative function, which is trained to distinguish real data pairs and two kinds of fake data pairs. The generators and discriminators are trained together using adversarial learning. Under mild assumptions, in theory the joint distributions characterized by the two generators concentrate to the data distribution. In experiments, three different kinds of domain pairs are considered, image-label, image-image and image-attribute pairs. Experiments on semi-supervised image classification, image-to-image translation and attribute-based image generation demonstrate the superiority of the proposed approach.

Author Information

Zhe Gan (Duke University)
Liqun Chen (Duke University)
Weiyao Wang (Duke University)
Yuchen Pu (Duke University)
Yizhe Zhang (Microsoft Research)
Hao Liu (Nanjing University)
Chunyuan Li (Duke University)
Lawrence Carin (Duke University)

More from the Same Authors