Autoencoding beyond pixels using a learned similarity metric
Abstract
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the GAN discriminator as basis for the VAE reconstruction objective. Thereby, we replace element-wise errors with feature-wise errors to better capture the data distribution while offering invariance towards e.g. translation. We apply our method to images of faces and show that it outperforms VAEs with element-wise similarity measures in terms of visual fidelity. Moreover, we show that the method learns an embedding in which high-level abstract visual features (e.g. wearing glasses) can be modified using simple arithmetic.
Cite
@article{arxiv.1512.09300,
title = {Autoencoding beyond pixels using a learned similarity metric},
author = {Anders Boesen Lindbo Larsen and Søren Kaae Sønderby and Hugo Larochelle and Ole Winther},
journal= {arXiv preprint arXiv:1512.09300},
year = {2016}
}