%0 Generic %1 abbasnejad2017bayesian %A Abbasnejad, M. Ehsan %A Shi, Qinfeng %A Abbasnejad, Iman %A Hengel, Anton van den %A Dick, Anthony %D 2017 %K bayesian conditional gan %T Bayesian Conditional Generative Adverserial Networks %U http://arxiv.org/abs/1706.05477 %X 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.

@misc{abbasnejad2017bayesian, abstract = {Traditional GANs use a deterministic generator function (typically a neural network) to transform a random noise input $z$ to a sample $\mathbf{x}$ 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 $\mathbf{x}$. 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.}, added-at = {2018-09-13T17:44:52.000+0200}, author = {Abbasnejad, M. Ehsan and Shi, Qinfeng and Abbasnejad, Iman and Hengel, Anton van den and Dick, Anthony}, biburl = {https://www.bibsonomy.org/bibtex/2dddcae4fd5c9ab18a904c4e7e27153c1/huntstart}, description = {[1706.05477] Bayesian Conditional Generative Adverserial Networks}, interhash = {8d5b2815e4015a264a55555853d38e11}, intrahash = {dddcae4fd5c9ab18a904c4e7e27153c1}, keywords = {bayesian conditional gan}, note = {cite arxiv:1706.05477}, timestamp = {2018-09-13T17:44:52.000+0200}, title = {Bayesian Conditional Generative Adverserial Networks}, url = {http://arxiv.org/abs/1706.05477}, year = 2017 }