Skip to main content

Learning weight uncertainty with stochastic gradient MCMC for shape classification

Publication ,  Conference
Li, C; Stevens, A; Chen, C; Pu, Y; Gan, Z; Carin, L
Published in: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
December 9, 2016

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.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

DOI

ISSN

1063-6919

ISBN

9781467388504

Publication Date

December 9, 2016

Volume

2016-December

Start / End Page

5666 / 5675
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Li, C., Stevens, A., Chen, C., Pu, Y., Gan, Z., & Carin, L. (2016). Learning weight uncertainty with stochastic gradient MCMC for shape classification. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 2016-December, pp. 5666–5675). https://doi.org/10.1109/CVPR.2016.611
Li, C., A. Stevens, C. Chen, Y. Pu, Z. Gan, and L. Carin. “Learning weight uncertainty with stochastic gradient MCMC for shape classification.” In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-December:5666–75, 2016. https://doi.org/10.1109/CVPR.2016.611.
Li C, Stevens A, Chen C, Pu Y, Gan Z, Carin L. Learning weight uncertainty with stochastic gradient MCMC for shape classification. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2016. p. 5666–75.
Li, C., et al. “Learning weight uncertainty with stochastic gradient MCMC for shape classification.” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, 2016, pp. 5666–75. Scopus, doi:10.1109/CVPR.2016.611.
Li C, Stevens A, Chen C, Pu Y, Gan Z, Carin L. Learning weight uncertainty with stochastic gradient MCMC for shape classification. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2016. p. 5666–5675.

Published In

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

DOI

ISSN

1063-6919

ISBN

9781467388504

Publication Date

December 9, 2016

Volume

2016-December

Start / End Page

5666 / 5675