Preprint · 2019 · Open access

Translation Insensitivity for Deep Convolutional Gaussian Processes

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

arXiv (Cornell University) · Published 15 February 2019

Read the free full textCite this paper

In brief

“Translation Insensitivity for Deep Convolutional Gaussian Processes” is a 2019 preprint by Vincent Dutordoir and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 10 citations as of 16 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
10
Most cited in
2020 (4)
References
24
Authors
5

Abstract

Deep learning has been at the foundation of large improvements in image classification. To improve the robustness of predictions, Bayesian approximations have been used to learn parameters in deep neural networks. We follow an alternative approach, by using Gaussian processes as building blocks for Bayesian deep learning models, which has recently become viable due to advances in inference for convolutional and deep structure. We investigate deep convolutional Gaussian processes, and identify a problem that holds back current performance. To remedy the issue, we introduce a translation insensitive convolutional kernel, which removes the restriction of requiring identical outputs for identical patch inputs. We show empirically that this convolutional kernel improves performances in both shallow and deep models. On MNIST, FASHION-MNIST and CIFAR-10 we improve previous GP models in terms of accuracy, with the addition of having more calibrated predictive probabilities than simple DNN models.

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., Tomczak, M. B., & Hensman, J. J. (2019). Translation Insensitivity for Deep Convolutional Gaussian Processes. arXiv (Cornell University). https://arxiv.org/pdf/1902.05888v1

MLA 9

Dutordoir, Vincent, et al. “Translation Insensitivity for Deep Convolutional Gaussian Processes.” arXiv (Cornell University), 2019. https://arxiv.org/pdf/1902.05888v1.

Chicago

Dutordoir, Vincent, Mark van der Wilk, Artem Artemev, Marcin B. Tomczak, and James J. Hensman. 2019. “Translation Insensitivity for Deep Convolutional Gaussian Processes.” arXiv (Cornell University). https://arxiv.org/pdf/1902.05888v1.

Harvard

Dutordoir, V. et al. (2019) ‘Translation Insensitivity for Deep Convolutional Gaussian Processes’, arXiv (Cornell University). Available at: https://arxiv.org/pdf/1902.05888v1.

IEEE

V. Dutordoir, M. van der Wilk, A. Artemev, M. B. Tomczak, and J. J. Hensman, “Translation Insensitivity for Deep Convolutional Gaussian Processes,” arXiv (Cornell University), 2019.

BibTeX

@misc{dutordoir2019translation,
  title     = {{Translation Insensitivity for Deep Convolutional Gaussian Processes}},
  author    = {Dutordoir, Vincent and van der Wilk, Mark and Artemev, Artem and Tomczak, Marcin B. and Hensman, James J.},
  howpublished = {arXiv (Cornell University)},
  year      = {2019},
  url       = {https://arxiv.org/pdf/1902.05888v1}
}

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

Citations by year

YearCitationsShare of the best year
201922
202044
202133
202211

Topic and keywords

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

  • translation invariance
  • Bayesian deep learning
  • image classification
  • uncertainty estimation
  • image patches

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., Tomczak, M. B., & Hensman, J. J. (2019). Translation Insensitivity for Deep Convolutional Gaussian Processes. arXiv (Cornell University). https://arxiv.org/pdf/1902.05888v1

How many times has this paper been cited?

10 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, Marcin B. Tomczak, James J. Hensman.

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.