Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Imbalanced Data

10/01/2019
by   Utkarsh Ojha, et al.
44

We propose a novel unsupervised generative model, Elastic-InfoGAN, that learns to disentangle object identity from other low-level aspects in class-imbalanced datasets. We first investigate the issues surrounding the assumptions about uniformity made by InfoGAN, and demonstrate its ineffectiveness to properly disentangle object identity in imbalanced data. Our key idea is to make the discovery of the discrete latent factor of variation invariant to identity-preserving transformations in real images, and use that as the signal to learn the latent distribution's parameters. Experiments on both artificial (MNIST) and real-world (YouTube-Faces) datasets demonstrate the effectiveness of our approach in imbalanced data by: (i) better disentanglement of object identity as a latent factor of variation; and (ii) better approximation of class imbalance in the data, as reflected in the learned parameters of the latent distribution.

READ FULL TEXT

page 2

page 4

page 7

page 8

page 11

research
06/21/2019

A Cyclically-Trained Adversarial Network for Invariant Representation Learning

We propose a cyclically-trained adversarial network to learn mappings fr...
research
06/09/2021

Stein Latent Optimization for GANs

Generative adversarial networks (GANs) with clustered latent spaces can ...
research
10/17/2022

Understanding CNN Fragility When Learning With Imbalanced Data

Convolutional neural networks (CNNs) have achieved impressive results on...
research
11/15/2017

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

Disentangling factors of variation has always been a challenging problem...
research
11/20/2017

Disentangling Factors of Variation by Mixing Them

We propose an unsupervised approach to learn image representations that ...
research
12/08/2021

CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning

In this paper, we propose a novel co-learning framework (CoSSL) with dec...
research
07/27/2021

Improving ClusterGAN Using Self-AugmentedInformation Maximization of Disentangling LatentSpaces

The Latent Space Clustering in Generative adversarial networks (ClusterG...

Please sign up or login with your details

Forgot password? Click here to reset