Learning weight uncertainty with stochastic gradient MCMC for shape classification

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

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

34 Scopus citations


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 (US)
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Societyhelp@computer.org
Number of pages10
ISBN (Print)9781467388504
StatePublished - Dec 9 2016
Externally publishedYes


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

Cite this