Preprint · 2014 · Open access

Convolutional Kernel Networks

Julien Mairal, Piotr Koniusz, Zaïd Harchaoui, Cordelia Schmid

arXiv (Cornell University), 27, 2627–2635 · Published 12 June 2014 · DOI 10.48550/arxiv.1406.3332

Open PDFView at the publisherCite this paper

In brief

“Convolutional Kernel Networks” is a 2014 preprint by Julien Mairal and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 308 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
308
Most cited in
2019 (41)
References
36
Authors
4

Abstract

An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is encoded by a reproducing kernel. Unlike traditional approaches where neural networks are learned either to represent data or for solving a classification task, our network learns to approximate the kernel feature map on training data. Such an approach enjoys several benefits over classical ones. First, by teaching CNNs to be invariant, we obtain simple network architectures that achieve a similar accuracy to more complex ones, while being easy to train and robust to overfitting. Second, we bridge a gap between the neural network literature and kernels, which are natural tools to model invariance. We evaluate our methodology on visual recognition tasks where CNNs have proven to perform well, e.g., digit recognition with the MNIST dataset, and the more challenging CIFAR-10 and STL-10 datasets, where our accuracy is competitive with the state of the art.

Cite this paper

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

APA 7

Mairal, J., Koniusz, P., Harchaoui, Z., & Schmid, C. (2014). Convolutional Kernel Networks. arXiv (Cornell University), 27, 2627–2635. https://doi.org/10.48550/arxiv.1406.3332

MLA 9

Mairal, Julien, et al. “Convolutional Kernel Networks.” arXiv (Cornell University), vol. 27, 2014, pp. 2627–2635. https://doi.org/10.48550/arxiv.1406.3332.

Chicago

Mairal, Julien, Piotr Koniusz, Zaïd Harchaoui, and Cordelia Schmid. 2014. “Convolutional Kernel Networks.” arXiv (Cornell University) 27: 2627–2635. https://doi.org/10.48550/arxiv.1406.3332.

Harvard

Mairal, J. et al. (2014) ‘Convolutional Kernel Networks’, arXiv (Cornell University), 27, pp. 2627–2635. doi:10.48550/arxiv.1406.3332.

IEEE

J. Mairal, P. Koniusz, Z. Harchaoui, and C. Schmid, “Convolutional Kernel Networks,” arXiv (Cornell University), vol. 27, pp. 2627–2635, 2014, doi: 10.48550/arxiv.1406.3332.

BibTeX

@misc{mairal2014convolutional,
  title     = {{Convolutional Kernel Networks}},
  author    = {Mairal, Julien and Koniusz, Piotr and Harchaoui, Zaïd and Schmid, Cordelia},
  howpublished = {arXiv (Cornell University)},
  year      = {2014},
  volume    = {27},
  pages     = {2627--2635},
  doi       = {10.48550/arxiv.1406.3332},
  url       = {https://doi.org/10.48550/arxiv.1406.3332}
}

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

Citations by year

YearCitationsShare of the best year
20173535
20182828
20194141
20203939
20212828
20222929
20231414
20241111
20251010
202655

Topic and keywords

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

  • reproducing kernels
  • transformation invariance
  • image representation learning
  • visual recognition
  • convolutional neural networks
  • digit recognition
  • CIFAR-10
  • STL-10

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?

Mairal, J., Koniusz, P., Harchaoui, Z., & Schmid, C. (2014). Convolutional Kernel Networks. arXiv (Cornell University), 27, 2627–2635. https://doi.org/10.48550/arxiv.1406.3332

How many times has this paper been cited?

308 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?

Julien Mairal, Piotr Koniusz, Zaïd Harchaoui, Cordelia Schmid.

What is the DOI of this paper?

10.48550/arxiv.1406.3332, permanently at https://doi.org/10.48550/arxiv.1406.3332. 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.