Bayesian Conditional Generative Adverserial Networks

2017/06/17 by M. Ehsan Abbasnejad, Qinfeng Shi, Abbasnejad, M. Ehsan +7
Computer Science · #Generative Adversarial Networks and Image Synthesis #Adversarial Robustness in Machine Learning #Gaussian Processes and Bayesian Inference

paper · pdf · doi:10.48550/arxiv.1706.05477

Abstract

Traditional GANs use a deterministic generator function (typically a neural network) to transform a random noise input z to a sample x that the discriminator seeks to distinguish. We propose a new GAN called Bayesian Conditional Generative Adversarial Networks (BC-GANs) that use a random generator function to transform a deterministic input y' to a sample x. Our BC-GANs extend traditional GANs to a Bayesian framework, and naturally handle unsupervised learning, supervised learning, and semi-supervised learning problems. Experiments show that the proposed BC-GANs outperforms the state-of-the-arts.

Citations

• Auto-Encoding Variational Bayes

Related

• A New Paradigm for Generative Adversarial Networks based on Randomized Decision Rules
• Probabilistic Generative Adversarial Networks
• Bidirectional Conditional Generative Adversarial Networks
• Conditional GANs with Auxiliary Discriminative Classifier
• Are conditional GANs explicitly conditional?