Jigsaw-VAE: Towards Balancing Features in Variational Autoencoders

05/12/2020
by   Saeid Asgari Taghanaki, et al.
5

The latent variables learned by VAEs have seen considerable interest as an unsupervised way of extracting features, which can then be used for downstream tasks. There is a growing interest in the question of whether features learned on one environment will generalize across different environments. We demonstrate here that VAE latent variables often focus on some factors of variation at the expense of others - in this case we refer to the features as “imbalanced”. Feature imbalance leads to poor generalization when the latent variables are used in an environment where the presence of features changes. Similarly, latent variables trained with imbalanced features induce the VAE to generate less diverse (i.e. biased towards dominant features) samples. To address this, we propose a regularization scheme for VAEs, which we show substantially addresses the feature imbalance problem. We also introduce a simple metric to measure the balance of features in generated images.

READ FULL TEXT

page 2

page 7

page 8

research
03/13/2023

Using VAEs to Learn Latent Variables: Observations on Applications in cryo-EM

Variational autoencoders (VAEs) are a popular generative model used to a...
research
05/27/2019

Quantization-Based Regularization for Autoencoders

Autoencoders and their variations provide unsupervised models for learni...
research
07/19/2018

Bounded Information Rate Variational Autoencoders

This paper introduces a new member of the family of Variational Autoenco...
research
02/05/2023

Latent Reconstruction-Aware Variational Autoencoder

Variational Autoencoders (VAEs) have become increasingly popular in rece...
research
09/26/2022

FONDUE: an algorithm to find the optimal dimensionality of the latent representations of variational autoencoders

When training a variational autoencoder (VAE) on a given dataset, determ...
research
04/20/2021

Decoding the shift-invariant data: applications for band-excitation scanning probe microscopy

A shift-invariant variational autoencoder (shift-VAE) is developed as an...
research
09/25/2019

Disentangling Speech and Non-Speech Components for Building Robust Acoustic Models from Found Data

In order to build language technologies for majority of the languages, i...

Please sign up or login with your details

Forgot password? Click here to reset