Learning weight uncertainty with stochastic gradient MCMC for shape classification

Published

Conference Paper

© 2016 IEEE. Learning the representation of shape cues in 2D & 3D objects for recognition is a fundamental task in computer vision. Deep neural networks (DNNs) have shown promising performance on this task. Due to the large variability of shapes, accurate recognition relies on good estimates of model uncertainty, ignored in traditional training of DNNs, typically learned via stochastic optimization. This paper leverages recent advances in stochastic gradient Markov Chain Monte Carlo (SG-MCMC) to learn weight uncertainty in DNNs. It yields principled Bayesian interpretations for the commonly used Dropout/DropConnect techniques and incorporates them into the SG-MCMC framework. Extensive experiments on 2D & 3D shape datasets and various DNN models demonstrate the superiority of the proposed approach over stochastic optimization. Our approach yields higher recognition accuracy when used in conjunction with Dropout and Batch-Normalization.

Full Text

Duke Authors

Cited Authors

  • Li, C; Stevens, A; Chen, C; Pu, Y; Gan, Z; Carin, L

Published Date

  • December 9, 2016

Published In

Volume / Issue

  • 2016-December /

Start / End Page

  • 5666 - 5675

International Standard Serial Number (ISSN)

  • 1063-6919

International Standard Book Number 13 (ISBN-13)

  • 9781467388504

Digital Object Identifier (DOI)

  • 10.1109/CVPR.2016.611

Citation Source

  • Scopus