DeepAI AI Chat
Log In Sign Up

Disentangling Factors of Variation by Mixing Them

by   Qiyang Hu, et al.
University of Maryland
Universität Bern

We propose an unsupervised approach to learn image representations that consist of disentangled factors of variation. A factor of variation corresponds to an image attribute that can be discerned consistently across a set of images, such as the pose or color of objects. Our disentangled representation consists of a concatenation of feature chunks, each chunk representing a factor of variation. It supports applications such as transferring attributes from one image to another, by simply swapping feature chunks, and classification or retrieval based on one or several attributes, by considering a user specified subset of feature chunks. We learn our representation in an unsupervised manner, without any labeling or knowledge of the data domain, using an autoencoder architecture with two novel training objectives: first, we propose an invariance objective to encourage that encoding of each attribute, and decoding of each chunk, are invariant to changes in other attributes and chunks, respectively, and second, we include a classification objective, which ensures that each chunk corresponds to a consistently discernible attribute in the represented image, hence avoiding the shortcut where chunks are ignored completely. We demonstrate the effectiveness of our approach on the MNIST, Sprites, and CelebA datasets.


page 5

page 6

page 7

page 8


A Cyclically-Trained Adversarial Network for Invariant Representation Learning

We propose a cyclically-trained adversarial network to learn mappings fr...

A Contrastive Objective for Learning Disentangled Representations

Learning representations of images that are invariant to sensitive or un...

Challenges in Disentangling Independent Factors of Variation

We study the problem of building models that disentangle independent fac...

An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild

Unsupervised disentanglement has been shown to be theoretically impossib...

DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images

Disentangling factors of variation has always been a challenging problem...

Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Imbalanced Data

We propose a novel unsupervised generative model, Elastic-InfoGAN, that ...

The Variational Fair Autoencoder

We investigate the problem of learning representations that are invarian...