Conference paper · 2016 · Open access

Wide Residual Networks

Sergey Zagoruyko, Nikos Komodakis

British Machine Vision Conference (BMVC), 87.1–87.12 · Published 1 January 2016 · DOI 10.5244/c.30.87

Open PDFView at the publisherCite this paper

In brief

“Wide Residual Networks” is a 2016 conference paper by Sergey Zagoruyko and Nikos Komodakis, published in British Machine Vision Conference (BMVC). OpenAlex counts 10,438 citations as of 19 November 2026, which puts it in the top 1% of works published in 2016 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
10,438
Most cited in
2023 (1,542)
Field-weighted impact
152.14
References
29
Authors
2

Abstract

Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very deep residual networks has a problem of diminishing feature reuse, which makes these networks very slow to train. To tackle these problems, in this paper we conduct a detailed experimental study on the architecture of ResNet blocks, based on which we propose a novel architecture where we decrease depth and increase width of residual networks. We call the resulting network structures wide residual networks (WRNs) and show that these are far superior over their commonly used thin and very deep counterparts. For example, we demonstrate that even a simple 16-layer-deep wide residual network outperforms in accuracy and efficiency all previous deep residual networks, including thousand-layer-deep networks, achieving new state-of-the-art results on CIFAR, SVHN, COCO, and significant improvements on ImageNet. Our code and models are available at https://github.com/szagoruyko/wide-residual-networks

Cite this paper

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

APA 7

Zagoruyko, S., & Komodakis, N. (2016). Wide Residual Networks. British Machine Vision Conference (BMVC), 87.1–87.12. https://doi.org/10.5244/c.30.87

MLA 9

Zagoruyko, Sergey, and Nikos Komodakis. “Wide Residual Networks.” British Machine Vision Conference (BMVC), 2016, pp. 87.1–87.12. https://doi.org/10.5244/c.30.87.

Chicago

Zagoruyko, Sergey and Nikos Komodakis. 2016. “Wide Residual Networks.” British Machine Vision Conference (BMVC): 87.1–87.12. https://doi.org/10.5244/c.30.87.

Harvard

Zagoruyko, S. and Komodakis, N. (2016) ‘Wide Residual Networks’, British Machine Vision Conference (BMVC), pp. 87.1–87.12. doi:10.5244/c.30.87.

IEEE

S. Zagoruyko and N. Komodakis, “Wide Residual Networks,” British Machine Vision Conference (BMVC), pp. 87.1–87.12, 2016, doi: 10.5244/c.30.87.

BibTeX

@inproceedings{zagoruyko2016wide,
  title     = {{Wide Residual Networks}},
  author    = {Zagoruyko, Sergey and Komodakis, Nikos},
  booktitle = {British Machine Vision Conference (BMVC)},
  year      = {2016},
  pages     = {87.1--87.12},
  doi       = {10.5244/c.30.87},
  url       = {https://doi.org/10.5244/c.30.87}
}

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

Citations by year

YearCitationsShare of the best year
2017225225
2018474474
2019746746
20201,0811081
20211,4001400
20221,3621362
20231,5421542
20241,4101410
20251,2711271
2026884884

Its field-weighted citation impact is 152.14: it has been cited 152.14 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

  • WideResNet
  • ResNet
  • network depth and width
  • feature reuse
  • training efficiency
  • image classification
  • ImageNet
  • CIFAR

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?

Zagoruyko, S., & Komodakis, N. (2016). Wide Residual Networks. British Machine Vision Conference (BMVC), 87.1–87.12. https://doi.org/10.5244/c.30.87

How many times has this paper been cited?

10,438 times, according to OpenAlex on 19 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?

Sergey Zagoruyko, Nikos Komodakis.

What is the DOI of this paper?

10.5244/c.30.87, permanently at https://doi.org/10.5244/c.30.87. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 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.