On Adversarial Mixup Resynthesis

Chris Beckham, Sina Honari, Vikas Verma, Alex Lamb, Farnoosh Ghadiri, R. Devon Hjelm, Yoshua Bengio, Chris Pal

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

In this paper, we explore new approaches to combining information encoded within the learned representations of autoencoders. We explore models that are capable of combining the attributes of multiple inputs such that a resynthesised output is trained to fool an adversarial discriminator for real versus synthesised data. Furthermore, we explore the use of such an architecture in the context of semi-supervised learning, where we learn a mixing function whose objective is to produce interpolations of hidden states, or masked combinations of latent representations that are consistent with a conditioned class label. We show quantitative and qualitative evidence that such a formulation is an interesting avenue of research.
Original languageEnglish
Title of host publication33rd Conference on Neural Information Processing Systems
Subtitle of host publicationNeurIPS 2019
PublisherNeural Information Processing Systems Foundation
Publication statusPublished - 2019
MoE publication typeA4 Article in a conference publication
EventConference on Neural Information Processing Systems - Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019
Conference number: 33
https://neurips.cc

Publication series

NameAdvances in Neural Information Processing Systems
ISSN (Electronic)1049-5258

Conference

ConferenceConference on Neural Information Processing Systems
Abbreviated titleNeurIPS
Country/TerritoryCanada
CityVancouver
Period08/12/201914/12/2019
Internet address

Keywords

  • Deep Learning

Fingerprint

Dive into the research topics of 'On Adversarial Mixup Resynthesis'. Together they form a unique fingerprint.

Cite this