Preprint · 2019 · Open access

Bayesian Image Classification with Deep Convolutional Gaussian Processes

Vincent Dutordoir, Mark van der Wilk, Artem Artemev, James J. Hensman

arXiv (Cornell University), 1529–1539 · Published 15 February 2019 · DOI 10.48550/arxiv.1902.05888

Free PDFView at the publisherCite this paper

In brief

“Bayesian Image Classification with Deep Convolutional Gaussian Processes” is a 2019 preprint by Vincent Dutordoir and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 25 citations as of 16 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
25
Most cited in
2021 (7)
References
27
Authors
4

Abstract

In decision-making systems, it is important to have classifiers that have calibrated uncertainties, with an optimisation objective that can be used for automated model selection and training. Gaussian processes (GPs) provide uncertainty estimates and a marginal likelihood objective, but their weak inductive biases lead to inferior accuracy. This has limited their applicability in certain tasks (e.g. image classification). We propose a translation-insensitive convolutional kernel, which relaxes the translation invariance constraint imposed by previous convolutional GPs. We show how we can use the marginal likelihood to learn the degree of insensitivity. We also reformulate GP image-to-image convolutional mappings as multi-output GPs, leading to deep convolutional GPs. We show experimentally that our new kernel improves performance in both single-layer and deep models. We also demonstrate that our fully Bayesian approach improves on dropout-based Bayesian deep learning methods in terms of uncertainty and marginal likelihood estimates.

Cite this paper

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

APA 7

Dutordoir, V., van der Wilk, M., Artemev, A., & Hensman, J. J. (2019). Bayesian Image Classification with Deep Convolutional Gaussian Processes. arXiv (Cornell University), 1529–1539. https://doi.org/10.48550/arxiv.1902.05888

MLA 9

Dutordoir, Vincent, et al. “Bayesian Image Classification with Deep Convolutional Gaussian Processes.” arXiv (Cornell University), 2019, pp. 1529–1539. https://doi.org/10.48550/arxiv.1902.05888.

Chicago

Dutordoir, Vincent, Mark van der Wilk, Artem Artemev, and James J. Hensman. 2019. “Bayesian Image Classification with Deep Convolutional Gaussian Processes.” arXiv (Cornell University): 1529–1539. https://doi.org/10.48550/arxiv.1902.05888.

Harvard

Dutordoir, V. et al. (2019) ‘Bayesian Image Classification with Deep Convolutional Gaussian Processes’, arXiv (Cornell University), pp. 1529–1539. doi:10.48550/arxiv.1902.05888.

IEEE

V. Dutordoir, M. van der Wilk, A. Artemev, and J. J. Hensman, “Bayesian Image Classification with Deep Convolutional Gaussian Processes,” arXiv (Cornell University), pp. 1529–1539, 2019, doi: 10.48550/arxiv.1902.05888.

BibTeX

@misc{dutordoir2019bayesian,
  title     = {{Bayesian Image Classification with Deep Convolutional Gaussian Processes}},
  author    = {Dutordoir, Vincent and van der Wilk, Mark and Artemev, Artem and Hensman, James J.},
  howpublished = {arXiv (Cornell University)},
  year      = {2019},
  pages     = {1529--1539},
  doi       = {10.48550/arxiv.1902.05888},
  url       = {https://doi.org/10.48550/arxiv.1902.05888}
}

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

Citations by year

YearCitationsShare of the best year
201922
202055
202177
202255
202333
202422
202511

Topic and keywords

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

  • image classification
  • uncertainty calibration
  • marginal likelihood
  • multi-output Gaussian processes
  • inductive bias

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?

Dutordoir, V., van der Wilk, M., Artemev, A., & Hensman, J. J. (2019). Bayesian Image Classification with Deep Convolutional Gaussian Processes. arXiv (Cornell University), 1529–1539. https://doi.org/10.48550/arxiv.1902.05888

How many times has this paper been cited?

25 times, according to OpenAlex on 16 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: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Vincent Dutordoir, Mark van der Wilk, Artem Artemev, James J. Hensman.

What is the DOI of this paper?

10.48550/arxiv.1902.05888. The permanent link is https://doi.org/10.48550/arxiv.1902.05888.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.