Ways of Conditioning Generative Adversarial Networks

• Main Authors: Kwak, Hanock, Zhang, Byoung-Tak
• Format: Journal Article
• Language: English
• Published: 04.11.2016
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Learning; Statistics - Machine Learning
• DOI: 10.48550/arxiv.1611.01455

The GANs are generative models whose random samples realistically reflect natural images. It also can generate samples with specific attributes by concatenating a condition vector into the input, yet research on this field is not well studied. We propose novel methods of conditioning generative adversarial networks (GANs) that achieve state-of-the-art results on MNIST and CIFAR-10. We mainly introduce two models: an information retrieving model that extracts conditional information from the samples, and a spatial bilinear pooling model that forms bilinear features derived from the spatial cross product of an image and a condition vector. These methods significantly enhance log-likelihood of test data under the conditional distributions compared to the methods of concatenation.