Preprint · 2018 · Open access

Calibrating Deep Convolutional Gaussian Processes

Gia-Lac Tran, Edwin V. Bonilla, John Patrick Cunningham, Pietro Michiardi A, Maurizio Filippone

arXiv (Cornell University) · Published 26 May 2018 · DOI 10.48550/arxiv.1805.10522

Open PDFView at the publisherCite this paper

In brief

“Calibrating Deep Convolutional Gaussian Processes” is a 2018 preprint by Gia-Lac Tran and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 31 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
31
Most cited in
2020 (10)
References
29
Authors
5

Abstract

The wide adoption of Convolutional Neural Networks (CNNs) in applications where decision-making under uncertainty is fundamental, has brought a great deal of attention to the ability of these models to accurately quantify the uncertainty in their predictions. Previous work on combining CNNs with Gaussian processes (GPs) has been developed under the assumption that the predictive probabilities of these models are well-calibrated. In this paper we show that, in fact, current combinations of CNNs and GPs are miscalibrated. We proposes a novel combination that considerably outperforms previous approaches on this aspect, while achieving state-of-the-art performance on image classification tasks.

Cite this paper

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

APA 7

Tran, G.-L., Bonilla, E. V., Cunningham, J. P., A, P. M., & Filippone, M. (2018). Calibrating Deep Convolutional Gaussian Processes. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1805.10522

MLA 9

Tran, Gia-Lac, et al. “Calibrating Deep Convolutional Gaussian Processes.” arXiv (Cornell University), 2018. https://doi.org/10.48550/arxiv.1805.10522.

Chicago

Tran, Gia-Lac, Edwin V. Bonilla, John Patrick Cunningham, Pietro Michiardi A, and Maurizio Filippone. 2018. “Calibrating Deep Convolutional Gaussian Processes.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1805.10522.

Harvard

Tran, G.-L. et al. (2018) ‘Calibrating Deep Convolutional Gaussian Processes’, arXiv (Cornell University). doi:10.48550/arxiv.1805.10522.

IEEE

G.-L. Tran, E. V. Bonilla, J. P. Cunningham, P. M. A, and M. Filippone, “Calibrating Deep Convolutional Gaussian Processes,” arXiv (Cornell University), 2018, doi: 10.48550/arxiv.1805.10522.

BibTeX

@misc{tran2018calibrating,
  title     = {{Calibrating Deep Convolutional Gaussian Processes}},
  author    = {Tran, Gia-Lac and Bonilla, Edwin V. and Cunningham, John Patrick and A, Pietro Michiardi and Filippone, Maurizio},
  howpublished = {arXiv (Cornell University)},
  year      = {2018},
  doi       = {10.48550/arxiv.1805.10522},
  url       = {https://doi.org/10.48550/arxiv.1805.10522}
}

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

Citations by year

YearCitationsShare of the best year
201811
201933
20201010
202166
202222
202344
202433
202522

Topic and keywords

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

  • uncertainty calibration
  • convolutional neural networks
  • Bayesian neural networks
  • image classification
  • uncertainty quantification

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?

Tran, G.-L., Bonilla, E. V., Cunningham, J. P., A, P. M., & Filippone, M. (2018). Calibrating Deep Convolutional Gaussian Processes. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1805.10522

How many times has this paper been cited?

31 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?

Gia-Lac Tran, Edwin V. Bonilla, John Patrick Cunningham, Pietro Michiardi A, Maurizio Filippone.

What is the DOI of this paper?

10.48550/arxiv.1805.10522, permanently at https://doi.org/10.48550/arxiv.1805.10522. 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.