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.
%0 Generic
%1 mirza2014conditional
%A Mirza, Mehdi
%A Osindero, Simon
%D 2014
%K GAN conditional
%T Conditional Generative Adversarial Nets
%U http://arxiv.org/abs/1411.1784
%X 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.
@misc{mirza2014conditional,
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.},
added-at = {2017-10-04T17:02:34.000+0200},
author = {Mirza, Mehdi and Osindero, Simon},
biburl = {https://www.bibsonomy.org/bibtex/2a4426d639ebb30270839ad347bcfb999/daschloer},
description = {Conditional Generative Adversarial Nets},
interhash = {efbbaeaebb1ea8d88264d258624d364c},
intrahash = {a4426d639ebb30270839ad347bcfb999},
keywords = {GAN conditional},
note = {cite arxiv:1411.1784},
timestamp = {2017-10-04T17:03:04.000+0200},
title = {Conditional Generative Adversarial Nets},
url = {http://arxiv.org/abs/1411.1784},
year = 2014
}