Semi-supervised Conditional GANs

Abstract

We introduce a new model for building conditional generative models in a semi-supervised setting to conditionally generate data given attributes by adapting the GAN framework. The proposed semi-supervised GAN (SS-GAN) model uses a pair of stacked discriminators to learn the marginal distribution of the data, and the conditional distribution of the attributes given the data respectively. In the semi-supervised setting, the marginal distribution (which is often harder to learn) is learned from the labeled + unlabeled data, and the conditional distribution is learned purely from the labeled data. Our experimental results demonstrate that this model performs significantly better compared to existing semi-supervised conditional GAN models.

References in corpus (3)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

Cited by in corpus (11)

• cGANs with Projection Discriminator
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• High-Fidelity Image Generation With Fewer Labels
• Generalizing semi-supervised generative adversarial networks to regression using feature contrasting
• Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation
• Transferring GANs: generating images from limited data
• cGANs with Multi-Hinge Loss
• Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
• Robust conditional GANs under missing or uncertain labels
• Hindsight Reward Tweaking via Conditional Deep Reinforcement Learning
• Selective Sampling and Mixture Models in Generative Adversarial Networks