Adversarial mixup resynthesizers

Christopher Beckham, Sina Honari, Vikas Verma, Alex Lamb, Farnoosh Ghadiri, R. Devon Hjelm, Christopher Pal

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaKonferenssiesitysScientificvertaisarvioitu

Abstrakti

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.

AlkuperäiskieliEnglanti
TilaJulkaistu - 1 tammik. 2019
OKM-julkaisutyyppiEi oikeutettu
TapahtumaDeep Generative Models for Highly Structured Data - New Orleans, Yhdysvallat
Kesto: 6 toukok. 20196 toukok. 2019

Workshop

WorkshopDeep Generative Models for Highly Structured Data
LyhennettäDGS@ICLR Workshop
Maa/AlueYhdysvallat
KaupunkiNew Orleans
Ajanjakso06/05/201906/05/2019
MuuDGS@ICLR Workshop

Sormenjälki

Sukella tutkimusaiheisiin 'Adversarial mixup resynthesizers'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä