DeepAI AI Chat
Log In Sign Up

Adversarial Autoencoders

11/18/2015
by   Alireza Makhzani, et al.
Google
UNIVERSITY OF TORONTO
0

In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior of the hidden code vector of the autoencoder with an arbitrary prior distribution. Matching the aggregated posterior to the prior ensures that generating from any part of prior space results in meaningful samples. As a result, the decoder of the adversarial autoencoder learns a deep generative model that maps the imposed prior to the data distribution. We show how the adversarial autoencoder can be used in applications such as semi-supervised classification, disentangling style and content of images, unsupervised clustering, dimensionality reduction and data visualization. We performed experiments on MNIST, Street View House Numbers and Toronto Face datasets and show that adversarial autoencoders achieve competitive results in generative modeling and semi-supervised classification tasks.

READ FULL TEXT

page 4

page 7

page 8

page 10

page 12

06/12/2019

Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders

We propose a vine copula autoencoder to construct flexible generative mo...
06/14/2019

Multi-Adversarial Variational Autoencoder Networks

The unsupervised training of GANs and VAEs has enabled them to generate ...
05/24/2018

Implicit Autoencoders

In this paper, we describe the "implicit autoencoder" (IAE), a generativ...
07/19/2018

Doubly Stochastic Adversarial Autoencoder

Any autoencoder network can be turned into a generative model by imposin...
02/13/2018

Learning Inverse Mappings with Adversarial Criterion

We propose a flipped-Adversarial AutoEncoder (FAAE) that simultaneously ...
07/15/2021

One-Class Classification for Wafer Map using Adversarial Autoencoder with DSVDD Prior

Recently, semiconductors' demand has exploded in virtual reality, smartp...
12/11/2018

Adversarial Autoencoders with Constant-Curvature Latent Manifolds

Constant-curvature Riemannian manifolds (CCMs) have been shown to be ide...

Code Repositories

adversarial_autoencoder

Implementation of Adversarial Autoencoder with Theano


view repo

AAE-tensorflow

Tensorflow implementation of Adversarial Autoencoders (https://arxiv.org/abs/1511.05644)


view repo

decorrelated-adversarial-autoencoder

Tensorflow implementation of Adversarial Autoencoders (with extra option to decorrelate style and classes)


view repo

AdversarialAutoEncoder

Adversarial AutoEncoder implemented with MXNet


view repo

chainer-adversarial-autoencoder

chainer implementation of Adversarial Autoencoder


view repo