Back to Search Start Over

Flipped-Adversarial AutoEncoders

Authors :
Zhang, Jiyi
Dang, Hung
Lee, Hwee Kuan
Chang, Ee-Chien
Publication Year :
2018

Abstract

We propose a flipped-Adversarial AutoEncoder (FAAE) that simultaneously trains a generative model G that maps an arbitrary latent code distribution to a data distribution and an encoder E that embodies an "inverse mapping" that encodes a data sample into a latent code vector. Unlike previous hybrid approaches that leverage adversarial training criterion in constructing autoencoders, FAAE minimizes re-encoding errors in the latent space and exploits adversarial criterion in the data space. Experimental evaluations demonstrate that the proposed framework produces sharper reconstructed images while at the same time enabling inference that captures rich semantic representation of data.

Subjects

Subjects :
Computer Science - Learning

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1802.04504
Document Type :
Working Paper