On Adversarial Mixup Resynthesis

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaKonferenssiesitysvertaisarvioitu

Tutkijat

  • Chris Beckham
  • Sina Honari
  • Vikas Verma

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

Organisaatiot

Kuvaus

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.

Yksityiskohdat

AlkuperäiskieliEnglanti
TilaJulkaistu - 2019
OKM-julkaisutyyppiEi oikeutettu
TapahtumaConference on Neural Information Processing Systems - Vancouver, Kanada
Kesto: 8 joulukuuta 201914 joulukuuta 2019
Konferenssinumero: 33
https://neurips.cc

Conference

ConferenceConference on Neural Information Processing Systems
LyhennettäNeurIPS
MaaKanada
KaupunkiVancouver
Ajanjakso08/12/201914/12/2019
www-osoite

ID: 38446382