Dissertation · 2019 · Open access

Bayesian Deep Learning and Uncertainty in Computer Vision

Buu Phan

UWSpace (University of Waterloo) · Published 17 September 2019

Open full textCite this paper

In brief

“Bayesian Deep Learning and Uncertainty in Computer Vision” is a 2019 dissertation by Buu Phan, published in UWSpace (University of Waterloo). OpenAlex counts 19 citations as of 22 November 2026. It is open access: the full text is free to read at UWSpace (University of Waterloo).

Citations
19
Most cited in
2022 (5)
References
81
Authors
1

Abstract

Visual data contains rich information about the operating environment of an intelligent robotic system. Extracting this information allows intelligent systems to reason and decide their future actions. Erroneous visual information, therefore, can lead to poor decisions, causing accidents and casualties, especially in a safety-critical application such as automated driving. One way to prevent this is by measuring the level of uncertainty in the visual information interpretation, so that the system knows the reliability degree of the extracted information. Deep neural networks are now being used in many vision tasks due to their superior accuracy compared to traditional machine learning methods. However, their estimated uncertainties have been shown to be unreliable. To mitigate this issue, researchers have developed methods and tools to apply Bayesian modeling to deep neural networks. This results in a class of models known as Bayesian neural networks, whose uncertainty estimates are more reliable and informative. In this thesis, we make the following contributions in the context of Bayesian Neural Network applied to vision tasks. In particular: - We improve the understanding of visual uncertainty estimates from Bayesian deep models. Specifically, we study the behavior of Bayesian deep models applied to road-scene image segmentation under different factors, such as varying weather, depth, and occlusion levels. - We show the importance of model calibration technique in the context of autonomous driving, which strengthens the reliability of the estimated uncertainty. We demonstrate its effectiveness in a simple object localization task. - We address the high run-time cost of the current Bayesian deep learning techniques. We develop a distillation technique based on the Dirichlet distribution, which allows us to estimate the uncertainties in real-time.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Phan, B. (2019). Bayesian Deep Learning and Uncertainty in Computer Vision. UWSpace (University of Waterloo). http://hdl.handle.net/10012/15056

MLA 9

Phan, Buu. “Bayesian Deep Learning and Uncertainty in Computer Vision.” UWSpace (University of Waterloo), 2019. http://hdl.handle.net/10012/15056.

Chicago

Phan, Buu. 2019. “Bayesian Deep Learning and Uncertainty in Computer Vision.” UWSpace (University of Waterloo). http://hdl.handle.net/10012/15056.

Harvard

Phan, B. (2019) ‘Bayesian Deep Learning and Uncertainty in Computer Vision’, UWSpace (University of Waterloo). Available at: http://hdl.handle.net/10012/15056.

IEEE

B. Phan, “Bayesian Deep Learning and Uncertainty in Computer Vision,” UWSpace (University of Waterloo), 2019.

BibTeX

@phdthesis{phan2019bayesian,
  title     = {{Bayesian Deep Learning and Uncertainty in Computer Vision}},
  author    = {Phan, Buu},
  year      = {2019},
  url       = {http://hdl.handle.net/10012/15056}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202011
202133
202255
202333
202433
202544

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • Bayesian neural networks
  • uncertainty estimation
  • computer vision
  • road scene segmentation
  • autonomous driving
  • model calibration
  • object localization
  • Dirichlet distribution

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Phan, B. (2019). Bayesian Deep Learning and Uncertainty in Computer Vision. UWSpace (University of Waterloo). http://hdl.handle.net/10012/15056

How many times has this paper been cited?

19 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at UWSpace (University of Waterloo): sign in and open the full text from this page.

Who wrote this paper?

Buu Phan.

Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.