Conference paper · 2020 · Open access

Fast Sparse ConvNets

Erich Elsen, Marat Dukhan, Trevor Gale, Karen Simonyan

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 14617–14626 · Published 1 June 2020 · DOI 10.1109/cvpr42600.2020.01464

Open PDFView at the publisherCite this paper

In brief

“Fast Sparse ConvNets” is a 2020 conference paper by Erich Elsen and 3 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 180 citations as of 19 November 2026, which puts it in the top 8% of works published in 2020 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
180
Most cited in
2021 (44)
Field-weighted impact
8.50
References
46
Authors
4

Abstract

Historically, the pursuit of efficient inference has been one of the driving forces behind the research into new deep learning architectures and building blocks. Some of the recent examples include: the squeeze-and-excitation module, depthwise separable convolutions in Xception, and the inverted bottleneck in MobileNet v2. Notably, in all of these cases, the resulting building blocks enabled not only higher efficiency, but also higher accuracy, and found wide adoption in the field. In this work, we further expand the arsenal of efficient building blocks for neural network architectures; but instead of combining standard primitives (such as convolution), we advocate for the replacement of these dense primitives with their sparse counterparts. While the idea of using sparsity to decrease the parameter count is not new, the conventional wisdom is that this reduction in theoretical FLOPs does not translate into real-world efficiency gains. We aim to correct this misconception by introducing a family of efficient sparse kernels for several hardware platforms, which we plan to open source for the benefit of the community. Equipped with our efficient implementation of sparse primitives, we show that sparse versions of MobileNet v1 and MobileNet v2 architectures substantially outperform strong dense baselines on the efficiency-accuracy curve. On Snapdragon 835 our sparse networks outperform their dense equivalents by 1.3 - 2.4× - equivalent to approximately one entire generation of improvement. We hope that our findings will facilitate wider adoption of sparsity as a tool for creating efficient and accurate deep learning architectures.

Cite this paper

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

APA 7

Elsen, E., Dukhan, M., Gale, T., & Simonyan, K. (2020). Fast Sparse ConvNets. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 14617–14626. https://doi.org/10.1109/cvpr42600.2020.01464

MLA 9

Elsen, Erich, et al. “Fast Sparse ConvNets.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2020, pp. 14617–14626. https://doi.org/10.1109/cvpr42600.2020.01464.

Chicago

Elsen, Erich, Marat Dukhan, Trevor Gale, and Karen Simonyan. 2020. “Fast Sparse ConvNets.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings: 14617–14626. https://doi.org/10.1109/cvpr42600.2020.01464.

Harvard

Elsen, E. et al. (2020) ‘Fast Sparse ConvNets’, IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 14617–14626. doi:10.1109/cvpr42600.2020.01464.

IEEE

E. Elsen, M. Dukhan, T. Gale, and K. Simonyan, “Fast Sparse ConvNets,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 14617–14626, 2020, doi: 10.1109/cvpr42600.2020.01464.

BibTeX

@inproceedings{elsen2020fast,
  title     = {{Fast Sparse ConvNets}},
  author    = {Elsen, Erich and Dukhan, Marat and Gale, Trevor and Simonyan, Karen},
  booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings},
  year      = {2020},
  pages     = {14617--14626},
  doi       = {10.1109/cvpr42600.2020.01464},
  url       = {https://doi.org/10.1109/cvpr42600.2020.01464}
}

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

Citations by year

YearCitationsShare of the best year
201922
20202424
20214444
20223232
20233030
20242424
20251515
202699

Its field-weighted citation impact is 8.50: it has been cited 8.50 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

  • sparse convolutional neural networks
  • sparse kernels
  • inference efficiency
  • MobileNetV1
  • MobileNetV2
  • hardware acceleration
  • FLOPs reduction
  • accuracy-efficiency trade-off

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?

Elsen, E., Dukhan, M., Gale, T., & Simonyan, K. (2020). Fast Sparse ConvNets. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 14617–14626. https://doi.org/10.1109/cvpr42600.2020.01464

How many times has this paper been cited?

180 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?

Erich Elsen, Marat Dukhan, Trevor Gale, Karen Simonyan.

What is the DOI of this paper?

10.1109/cvpr42600.2020.01464, permanently at https://doi.org/10.1109/cvpr42600.2020.01464. 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.