Bayesian GAN

05/26/2017
by   Yunus Saatchi, et al.
0

Generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood. We present a practical Bayesian formulation for unsupervised and semi-supervised learning with GANs. Within this framework, we use stochastic gradient Hamiltonian Monte Carlo to marginalize the weights of the generator and discriminator networks. The resulting approach is straightforward and obtains good performance without any standard interventions such as feature matching, or mini-batch discrimination. By exploring an expressive posterior over the parameters of the generator, the Bayesian GAN avoids mode-collapse, produces interpretable and diverse candidate samples, and provides state-of-the-art quantitative results for semi-supervised learning on benchmarks including SVHN, CelebA, and CIFAR-10, outperforming DCGAN, Wasserstein GANs, and DCGAN ensembles.

READ FULL TEXT

page 10

page 12

page 15

page 16

research
05/27/2017

Good Semi-supervised Learning that Requires a Bad GAN

Semi-supervised learning methods based on generative adversarial network...
research
06/17/2017

Bayesian Conditional Generative Adverserial Networks

Traditional GANs use a deterministic generator function (typically a neu...
research
05/23/2018

Semi-Supervised Learning with GANs: Revisiting Manifold Regularization

GANS are powerful generative models that are able to model the manifold ...
research
05/25/2018

Detecting Deceptive Reviews using Generative Adversarial Networks

In the past few years, consumer review sites have become the main target...
research
10/29/2020

Teaching a GAN What Not to Learn

Generative adversarial networks (GANs) were originally envisioned as uns...
research
03/21/2023

Linking generative semi-supervised learning and generative open-set recognition

This study investigates the relationship between semi-supervised learnin...
research
09/01/2018

Semi-supervised Learning on Graphs with Generative Adversarial Nets

We investigate how generative adversarial nets (GANs) can help semi-supe...

Please sign up or login with your details

Forgot password? Click here to reset