Conditional Generative Adversarial Nets
Mehdi Mirza, Simon Osindero · arXiv (Cornell University) · 2014
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.
Cited by 8,217 works. doi:10.48550/arxiv.1411.1784 Open-access PDF
Authors
References
- Improving neural networks by preventing co-adaptation of feature detectors
- Efficient Estimation of Word Representations in Vector Space
- GAN(Generative Adversarial Nets)
- What is the best multi-stage architecture for object recognition?
- Going Deeper with Convolutions
- Pylearn2: a machine learning research library
- DeViSE: A Deep Visual-Semantic Embedding Model
- Noise-contrastive estimation: A new estimation principle for unnormalized statistical models
- Deep Generative Stochastic Networks Trainable by Backprop
- Multimodal Neural Language Models