Adversarial Latent Autoencoders

04/09/2020
by   Stanislav Pidhorskyi, et al.
0

Autoencoder networks are unsupervised approaches aiming at combining generative and representational properties by learning simultaneously an encoder-generator map. Although studied extensively, the issues of whether they have the same generative power of GANs, or learn disentangled representations, have not been fully addressed. We introduce an autoencoder that tackles these issues jointly, which we call Adversarial Latent Autoencoder (ALAE). It is a general architecture that can leverage recent improvements on GAN training procedures. We designed two autoencoders: one based on a MLP encoder, and another based on a StyleGAN generator, which we call StyleALAE. We verify the disentanglement properties of both architectures. We show that StyleALAE can not only generate 1024x1024 face images with comparable quality of StyleGAN, but at the same resolution can also produce face reconstructions and manipulations based on real images. This makes ALAE the first autoencoder able to compare with, and go beyond the capabilities of a generator-only type of architecture.

READ FULL TEXT

page 5

page 7

page 8

research
04/07/2017

It Takes (Only) Two: Adversarial Generator-Encoder Networks

We present a new autoencoder-type architecture that is trainable in an u...
research
12/19/2018

An Empirical Study of Generative Models with Encoders

Generative adversarial networks (GANs) are capable of producing high qua...
research
04/12/2019

Towards Photographic Image Manipulation with Balanced Growing of Generative Autoencoders

We build on recent advances in progressively growing generative autoenco...
research
06/17/2020

Disrupting Deepfakes with an Adversarial Attack that Survives Training

The rapid progress in generative models and autoencoders has given rise ...
research
06/13/2017

Adversarially Regularized Autoencoders

While autoencoders are a key technique in representation learning for co...
research
01/22/2020

Towards A Controllable Disentanglement Network

This paper addresses two crucial problems of learning disentangled image...
research
06/11/2020

End-to-end Sinkhorn Autoencoder with Noise Generator

In this work, we propose a novel end-to-end sinkhorn autoencoder with no...

Please sign up or login with your details

Forgot password? Click here to reset