Skip to main navigation Skip to search Skip to main content

Learning weight uncertainty with stochastic gradient MCMC for shape classification

  • Chunyuan Li
  • , Andrew Stevens
  • , Changyou Chen
  • , Yunchen Pu
  • , Zhe Gan
  • , Lawrence Carin
  • Duke University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

40 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PublisherIEEE Computer Society
Pages5666-5675
Number of pages10
ISBN (Electronic)9781467388504
DOIs
StatePublished - Dec 9 2016
Event29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States
Duration: Jun 26 2016Jul 1 2016

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2016-December
ISSN (Print)1063-6919

Conference

Conference29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Country/TerritoryUnited States
CityLas Vegas
Period06/26/1607/1/16

Fingerprint

Dive into the research topics of 'Learning weight uncertainty with stochastic gradient MCMC for shape classification'. Together they form a unique fingerprint.

Cite this