Conditional Generative Adversarial Nets

Abstract

Generative Adversarial Nets [8] were recently introduced as a novel way to train generative models. In this work we introduce the conditional version of generative adversarial nets, which can be constructed by simply feeding the data, y, we wish to condition on to both the generator and discriminator. We show that this model can generate MNIST digits conditioned on class labels. We also illustrate how this model could be used to learn a multi-modal model, and provide preliminary examples of an application to image tagging in which we demonstrate how this approach can generate descriptive tags which are not part of training labels.

References in corpus (3)

• Improving neural networks by preventing co-adaptation of feature detectors
• Going Deeper with Convolutions
• Better Mixing via Deep Representations

Cited by in corpus (22)

• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Adversarial Discriminative Domain Adaptation
• Unsupervised Cross-Domain Image Generation
• Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
• Disentangling factors of variation in deep representations using adversarial training
• Mode Regularized Generative Adversarial Networks
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
• TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
• Age Progression/Regression by Conditional Adversarial Autoencoder
• Generative Adversarial Residual Pairwise Networks for One Shot Learning
• Unsupervised Image-to-Image Translation with Generative Adversarial Networks
• A Point Set Generation Network for 3D Object Reconstruction from a Single Image
• Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network
• Transformation-Grounded Image Generation Network for Novel 3D View Synthesis
• Model-based Adversarial Imitation Learning
• Message Passing Multi-Agent GANs
• Synthetic to Real Adaptation with Generative Correlation Alignment Networks
• Task Specific Adversarial Cost Function
• Ways of Conditioning Generative Adversarial Networks
• Generative Class-conditional Autoencoders
• CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation
• Awesome Typography: Statistics-Based Text Effects Transfer