Autoencoding beyond pixels using a learned similarity metric
Autoencoding beyond pixels using a learned similarity metric
Autoencoding beyond pixels using a learned similarity metric

Autoencoding beyond pixels using a learned similarity metric

We present an autoencoder that leverages learned representations to better measure similarities in data space.
Article
Reading time:
By
Anders Boesen Lindbo Larsen, Søren Kaae Sønderby, Hugo Larochelle, Ole Winther
TABLE OF CONTENTS

Discover Raffle Search

An AI search engine that simplifies data management, analysis, and insights for smarter business decisions and market strategies.

Explore our Research

By combining a variational autoencoder with a generative adversarial network, we can use learned feature representations in the GAN discriminator as a basis for the VAE reconstruction objective.

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.

Download

Autoencoding beyond pixels using a learned similarity metric
Autoencoding beyond pixels using a learned similarity metric

Autoencoding beyond pixels using a learned similarity metric

We present an autoencoder that leverages learned representations to better measure similarities in data space.

Explore our Research

By combining a variational autoencoder with a generative adversarial network, we can use learned feature representations in the GAN discriminator as a basis for the VAE reconstruction objective.

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.

Download

Don't miss any update!
SOC2 badge