Gaussian Process Deep Belief Networks: A Smooth Generative Model of Shape with Uncertainty Propagation

  • Alessandro Di Martino

Student thesis: Doctoral ThesisPhD

Abstract

The shape of an object is an important characteristic for many vision problems such as segmentation, detection and tracking. Being independent of appearance, it is possible to generalise to a large range of objects from only small amounts of data. However, shapes represented as silhouette images are challenging to model due to complicated likelihood functions leading to intractable posteriors. In this work we present a generative model of shapes which provides a low-dimensional latent encoding which importantly resides on a smooth manifold with respect to the silhouette images. The proposed model propagates uncertainty in a principled manner allowing it to learn from small amounts of data and providing predictions with associated uncertainty. Our experiments show that the proposed model provides favourable quantitative results compared with the state-of-the-art while simultaneously providing a representation that resides on a low-dimensional interpretable manifold.
Date of Award19 Nov 2019
Original languageEnglish
Awarding Institution
  • University of Bath
SupervisorNeill Campbell (Supervisor) & Darren Cosker (Supervisor)

Keywords

  • Gaussian Processes
  • Deep Belief Networks
  • Deep Learning
  • Manifolds
  • Shape Models
  • Generative Models

Cite this

Gaussian Process Deep Belief Networks: A Smooth Generative Model of Shape with Uncertainty Propagation
Di Martino, A. (Author). 19 Nov 2019

Student thesis: Doctoral ThesisPhD