Preprint · 2016 · Open access

End-to-End Kernel Learning with Supervised Convolutional Kernel Networks

Julien Mairal

arXiv (Cornell University), 1399–1407 · Published 20 May 2016 · DOI 10.48550/arxiv.1605.06265

Free PDFView at the publisherCite this paper

In brief

“End-to-End Kernel Learning with Supervised Convolutional Kernel Networks” is a 2016 preprint by Julien Mairal, published in arXiv (Cornell University). OpenAlex counts 93 citations as of 16 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
93
Most cited in
2019 (21)
References
34
Authors
1

Abstract

In this paper, we introduce a new image representation based on a multilayer kernel machine. Unlike traditional kernel methods where data representation is decoupled from the prediction task, we learn how to shape the kernel with supervision. We proceed by first proposing improvements of the recently-introduced convolutional kernel networks (CKNs) in the context of unsupervised learning; then, we derive backpropagation rules to take advantage of labeled training data. The resulting model is a new type of convolutional neural network, where optimizing the filters at each layer is equivalent to learning a linear subspace in a reproducing kernel Hilbert space (RKHS). We show that our method achieves reasonably competitive performance for image classification on some standard "deep learning" datasets such as CIFAR-10 and SVHN, and also for image super-resolution, demonstrating the applicability of our approach to a large variety of image-related tasks.

Cite this paper

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

APA 7

Mairal, J. (2016). End-to-End Kernel Learning with Supervised Convolutional Kernel Networks. arXiv (Cornell University), 1399–1407. https://doi.org/10.48550/arxiv.1605.06265

MLA 9

Mairal, Julien. “End-to-End Kernel Learning with Supervised Convolutional Kernel Networks.” arXiv (Cornell University), 2016, pp. 1399–1407. https://doi.org/10.48550/arxiv.1605.06265.

Chicago

Mairal, Julien. 2016. “End-to-End Kernel Learning with Supervised Convolutional Kernel Networks.” arXiv (Cornell University): 1399–1407. https://doi.org/10.48550/arxiv.1605.06265.

Harvard

Mairal, J. (2016) ‘End-to-End Kernel Learning with Supervised Convolutional Kernel Networks’, arXiv (Cornell University), pp. 1399–1407. doi:10.48550/arxiv.1605.06265.

IEEE

J. Mairal, “End-to-End Kernel Learning with Supervised Convolutional Kernel Networks,” arXiv (Cornell University), pp. 1399–1407, 2016, doi: 10.48550/arxiv.1605.06265.

BibTeX

@misc{mairal2016kernel,
  title     = {{End-to-End Kernel Learning with Supervised Convolutional Kernel Networks}},
  author    = {Mairal, Julien},
  howpublished = {arXiv (Cornell University)},
  year      = {2016},
  pages     = {1399--1407},
  doi       = {10.48550/arxiv.1605.06265},
  url       = {https://doi.org/10.48550/arxiv.1605.06265}
}

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

Citations by year

YearCitationsShare of the best year
201611
201799
201888
20192121
20201818
202188
20221313
202388
202466
202611

Topic and keywords

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

  • reproducing kernel Hilbert space
  • image representation
  • image classification
  • image super-resolution
  • end-to-end learning

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. (2016). End-to-End Kernel Learning with Supervised Convolutional Kernel Networks. arXiv (Cornell University), 1399–1407. https://doi.org/10.48550/arxiv.1605.06265

How many times has this paper been cited?

93 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?

Julien Mairal.

What is the DOI of this paper?

10.48550/arxiv.1605.06265. The permanent link is https://doi.org/10.48550/arxiv.1605.06265.

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.