Geometry of Deep Generative Models for Disentangled Representations

Ankita Shukla, Shagun Uppal, Sarthak Bhagat, Saket Anand, Pavan Turaga

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning a set of low-dimensional latent-space variables and an embedding function. The geometrical properties of these latent spaces has been studied under the lens of Riemannian geometry; via analysis of the non-linearity of the generator function. In new developments, deep generative models have been used for learning semantically meaningful 'disentangled' representations; that capture task relevant attributes while being invariant to other attributes. In this work, we explore the geometry of popular generative models for disentangled representation learning. We use several metrics to compare the properties of latent spaces of disentangled representation models in terms of class separability and curvature of the latent-space. The proposed study establishes that the class distinguishable features in the disentangled latent space exhibits higher curvature as opposed to a variational autoencoder. We evaluate and compare the geometry of three such models with variational autoencoder on two different datasets. The proposed study shows that the distances and interpolations in the latent space are significantly improved with Riemannian metric owing to the curvature of the space.

Original languageEnglish (US)
Title of host publicationProceedings - 11th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2018
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450366151
DOIs
StatePublished - Dec 18 2018
Event11th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2018 - Hyderabad, India
Duration: Dec 18 2018Dec 22 2018

Publication series

NameACM International Conference Proceeding Series

Conference

Conference11th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2018
CountryIndia
CityHyderabad
Period12/18/1812/22/18

Keywords

  • Deep generative models
  • Disentangled representations
  • Riemannian Geometry

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint Dive into the research topics of 'Geometry of Deep Generative Models for Disentangled Representations'. Together they form a unique fingerprint.

Cite this