On Adversarial Mixup Resynthesis

Research output: Contribution to conferencePaperScientificpeer-review

Researchers

  • Chris Beckham
  • Sina Honari
  • Vikas Verma

  • Alex Lamb
  • Farnoosh Ghadiri
  • R. Devon Hjelm
  • Yoshua Bengio
  • Chris Pal

Research units

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.

Details

Original languageEnglish
Publication statusPublished - 2019
MoE publication typeNot Eligible
EventConference on Neural Information Processing Systems - Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019
Conference number: 33
https://neurips.cc

Conference

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

    Research areas

  • Deep Learning

ID: 38446382