Conference paper · 2020 · Open access

Scalable Uncertainty for Computer Vision With Functional Variational Inference

Eduardo D C Carvalho, Ronald Clark, Andrea Nicastro, Paul H. J. Kelly

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 12000–12010 · Published 1 June 2020 · DOI 10.1109/cvpr42600.2020.01202

Open PDFView at the publisherCite this paper

In brief

“Scalable Uncertainty for Computer Vision With Functional Variational Inference” is a 2020 conference paper by Eduardo D C Carvalho and 3 co-authors, published in IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings. OpenAlex counts 24 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
24
Most cited in
2021 (6)
Field-weighted impact
1.04
References
56
Authors
4

Abstract

As Deep Learning continues to yield successful applications in Computer Vision, the ability to quantify all forms of uncertainty is a paramount requirement for its safe and reliable deployment in the real-world. In this work, we leverage the formulation of variational inference in function space, where we associate Gaussian Processes (GPs) to both Bayesian CNN priors and variational family. Since GPs are fully determined by their mean and covariance functions, we are able to obtain predictive uncertainty estimates at the cost of a single forward pass through any chosen CNN architecture and for any supervised learning task. By leveraging the structure of the induced covariance matrices, we propose numerically efficient algorithms which enable fast training in the context of high-dimensional tasks such as depth estimation and semantic segmentation. Additionally, we provide sufficient conditions for constructing regression loss functions whose probabilistic counterparts are compatible with aleatoric uncertainty quantification.

Cite this paper

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

APA 7

Carvalho, E. D. C., Clark, R., Nicastro, A., & Kelly, P. H. J. (2020). Scalable Uncertainty for Computer Vision With Functional Variational Inference. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 12000–12010. https://doi.org/10.1109/cvpr42600.2020.01202

MLA 9

Carvalho, Eduardo D C, et al. “Scalable Uncertainty for Computer Vision With Functional Variational Inference.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2020, pp. 12000–12010. https://doi.org/10.1109/cvpr42600.2020.01202.

Chicago

Carvalho, Eduardo D C, Ronald Clark, Andrea Nicastro, and Paul H. J. Kelly. 2020. “Scalable Uncertainty for Computer Vision With Functional Variational Inference.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings: 12000–12010. https://doi.org/10.1109/cvpr42600.2020.01202.

Harvard

Carvalho, E. D. C. et al. (2020) ‘Scalable Uncertainty for Computer Vision With Functional Variational Inference’, IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 12000–12010. doi:10.1109/cvpr42600.2020.01202.

IEEE

E. D. C. Carvalho, R. Clark, A. Nicastro, and P. H. J. Kelly, “Scalable Uncertainty for Computer Vision With Functional Variational Inference,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 12000–12010, 2020, doi: 10.1109/cvpr42600.2020.01202.

BibTeX

@inproceedings{carvalho2020scalable,
  title     = {{Scalable Uncertainty for Computer Vision With Functional Variational Inference}},
  author    = {Carvalho, Eduardo D C and Clark, Ronald and Nicastro, Andrea and Kelly, Paul H. J.},
  booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings},
  year      = {2020},
  pages     = {12000--12010},
  doi       = {10.1109/cvpr42600.2020.01202},
  url       = {https://doi.org/10.1109/cvpr42600.2020.01202}
}

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

Citations by year

YearCitationsShare of the best year
202011
202166
202255
202355
202455
202622

Its field-weighted citation impact is 1.04: it has been cited 1.04 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Gaussian Processes and Bayesian Inference

  • uncertainty quantification
  • Gaussian processes
  • Bayesian convolutional neural network
  • aleatoric uncertainty
  • depth estimation
  • semantic segmentation

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?

Carvalho, E. D. C., Clark, R., Nicastro, A., & Kelly, P. H. J. (2020). Scalable Uncertainty for Computer Vision With Functional Variational Inference. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 12000–12010. https://doi.org/10.1109/cvpr42600.2020.01202

How many times has this paper been cited?

24 times, according to OpenAlex on 18 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Eduardo D C Carvalho, Ronald Clark, Andrea Nicastro, Paul H. J. Kelly.

What is the DOI of this paper?

10.1109/cvpr42600.2020.01202, permanently at https://doi.org/10.1109/cvpr42600.2020.01202. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 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.