University of Surrey

Test tubes in the lab Research in the ATI Dance Research

VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning

Srivastava, A, Valkoz, L, Russell, Christopher, Gutmann, MU and Sutton, C (2017) VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning In: 31st Conference on Neural Information Processing Systems (NIPS 2017), 4 - 9 December 2017, Long Beach, CA, USA..

[img] Text
6923-veegan-reducing-mode-collapse-in-gans-using-implicit-variational-learning.pdf - Accepted version Manuscript
Restricted to Repository staff only until 4 December 2018.

Download (883kB)

Abstract

Deep generative models provide powerful tools for distributions over complicated manifolds, such as those of natural images. But many of these methods, including generative adversarial networks (GANs), can be difficult to train, in part because they are prone to mode collapse, which means that they characterize only a few modes of the true distribution. To address this, we introduce VEEGAN, which features a reconstructor network, reversing the action of the generator by mapping from data to noise. Our training objective retains the original asymptotic consistency guarantee of GANs, and can be interpreted as a novel autoencoder loss over the noise. In sharp contrast to a traditional autoencoder over data points, VEEGAN does not require specifying a loss function over the data, but rather only over the representations, which are standard normal by assumption. On an extensive set of synthetic and real world image datasets, VEEGAN indeed resists mode collapsing to a far greater extent than other recent GAN variants, and produces more realistic samples.

Item Type: Conference or Workshop Item (Conference Poster)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Srivastava, AUNSPECIFIEDUNSPECIFIED
Valkoz, LUNSPECIFIEDUNSPECIFIED
Russell, Christopherchris.russell@surrey.ac.ukUNSPECIFIED
Gutmann, MUUNSPECIFIEDUNSPECIFIED
Sutton, CUNSPECIFIEDUNSPECIFIED
Date : 4 December 2017
Copyright Disclaimer : Copyright 2017 MIT Press
Related URLs :
Depositing User : Melanie Hughes
Date Deposited : 28 Nov 2017 12:40
Last Modified : 28 Nov 2017 12:40
URI: http://epubs.surrey.ac.uk/id/eprint/845053

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800