Conference paper · 2015 · Open access

Efficient and accurate approximations of nonlinear convolutional networks

Xiangyu Zhang, Jianhua Zou, Ming Xiang, Kaiming He, Jian Sun

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 1984–1992 · Published 1 June 2015 · DOI 10.1109/cvpr.2015.7298809

Open PDFView at the publisherCite this paper

In brief

“Efficient and accurate approximations of nonlinear convolutional networks” is a 2015 conference paper by Xiangyu Zhang and 4 co-authors, published in IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings. OpenAlex counts 304 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
304
Most cited in
2019 (43)
Field-weighted impact
10.67
References
28
Authors
5

Abstract

This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs). Unlike existing methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into account. We minimize the reconstruction error of the nonlinear responses, subject to a low-rank constraint which helps to reduce the complexity of filters. We develop an effective solution to this constrained nonlinear optimization problem. An algorithm is also presented for reducing the accumulated error when multiple layers are approximated. A whole-model speedup ratio of 4× is demonstrated on a large network trained for ImageNet, while the top-5 error rate is only increased by 0.9%. Our accelerated model has a comparably fast speed as the “AlexNet” [11], but is 4.7% more accurate.

Cite this paper

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

APA 7

Zhang, X., Zou, J., Xiang, M., He, K., & Sun, J. (2015). Efficient and accurate approximations of nonlinear convolutional networks. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 1984–1992. https://doi.org/10.1109/cvpr.2015.7298809

MLA 9

Zhang, Xiangyu, et al. “Efficient and accurate approximations of nonlinear convolutional networks.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2015, pp. 1984–1992. https://doi.org/10.1109/cvpr.2015.7298809.

Chicago

Zhang, Xiangyu, Jianhua Zou, Ming Xiang, Kaiming He, and Jian Sun. 2015. “Efficient and accurate approximations of nonlinear convolutional networks.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings: 1984–1992. https://doi.org/10.1109/cvpr.2015.7298809.

Harvard

Zhang, X. et al. (2015) ‘Efficient and accurate approximations of nonlinear convolutional networks’, IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 1984–1992. doi:10.1109/cvpr.2015.7298809.

IEEE

X. Zhang, J. Zou, M. Xiang, K. He, and J. Sun, “Efficient and accurate approximations of nonlinear convolutional networks,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 1984–1992, 2015, doi: 10.1109/cvpr.2015.7298809.

BibTeX

@inproceedings{zhang2015efficient,
  title     = {{Efficient and accurate approximations of nonlinear convolutional networks}},
  author    = {Zhang, Xiangyu and Zou, Jianhua and Xiang, Ming and He, Kaiming and Sun, Jian},
  booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings},
  year      = {2015},
  pages     = {1984--1992},
  doi       = {10.1109/cvpr.2015.7298809},
  url       = {https://doi.org/10.1109/cvpr.2015.7298809}
}

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

Citations by year

YearCitationsShare of the best year
20172626
20183535
20194343
20204141
20213939
20222525
20232626
20242121
20251111
202677

Its field-weighted citation impact is 10.67: it has been cited 10.67 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

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

  • low-rank approximation
  • nonlinear programming
  • ImageNet
  • AlexNet

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?

Zhang, X., Zou, J., Xiang, M., He, K., & Sun, J. (2015). Efficient and accurate approximations of nonlinear convolutional networks. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 1984–1992. https://doi.org/10.1109/cvpr.2015.7298809

How many times has this paper been cited?

304 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?

Xiangyu Zhang, Jianhua Zou, Ming Xiang, Kaiming He, Jian Sun.

What is the DOI of this paper?

10.1109/cvpr.2015.7298809, permanently at https://doi.org/10.1109/cvpr.2015.7298809. 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.