Preprint · 2016 · Open access

Faster CNNs with Direct Sparse Convolutions and Guided Pruning

Jongsoo Park, Sheng Li, Wei Xiong Wen, Ping Tak Peter Tang, Hai Helen Li, Yiran Chen, Pradeep Kumar Dubey

arXiv (Cornell University) · Published 4 August 2016 · DOI 10.48550/arxiv.1608.01409

Open PDFView at the publisherCite this paper

In brief

“Faster CNNs with Direct Sparse Convolutions and Guided Pruning” is a 2016 preprint by Jongsoo Park and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 192 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
192
Most cited in
2021 (35)
References
31
Authors
7

Abstract

Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and undesirable. Consequently, various methods have been developed to prune a CNN once it is trained. Nevertheless, the resulting CNNs offer limited benefits. While pruning the fully connected layers reduces a CNN's size considerably, it does not improve inference speed noticeably as the compute heavy parts lie in convolutions. Pruning CNNs in a way that increase inference speed often imposes specific sparsity structures, thus limiting the achievable sparsity levels. We present a method to realize simultaneously size economy and speed improvement while pruning CNNs. Paramount to our success is an efficient general sparse-with-dense matrix multiplication implementation that is applicable to convolution of feature maps with kernels of arbitrary sparsity patterns. Complementing this, we developed a performance model that predicts sweet spots of sparsity levels for different layers and on different computer architectures. Together, these two allow us to demonstrate 3.1--7.3$\times$ convolution speedups over dense convolution in AlexNet, on Intel Atom, Xeon, and Xeon Phi processors, spanning the spectrum from mobile devices to supercomputers. We also open source our project at https://github.com/IntelLabs/SkimCaffe.

Cite this paper

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

APA 7

Park, J., Li, S., Wen, W. X., Tang, P. T. P., Li, H. H., Chen, Y., & Dubey, P. K. (2016). Faster CNNs with Direct Sparse Convolutions and Guided Pruning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1608.01409

MLA 9

Park, Jongsoo, et al. “Faster CNNs with Direct Sparse Convolutions and Guided Pruning.” arXiv (Cornell University), 2016. https://doi.org/10.48550/arxiv.1608.01409.

Chicago

Park, Jongsoo, Sheng Li, Wei Xiong Wen, Ping Tak Peter Tang, Hai Helen Li, Yiran Chen, and Pradeep Kumar Dubey. 2016. “Faster CNNs with Direct Sparse Convolutions and Guided Pruning.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1608.01409.

Harvard

Park, J. et al. (2016) ‘Faster CNNs with Direct Sparse Convolutions and Guided Pruning’, arXiv (Cornell University). doi:10.48550/arxiv.1608.01409.

IEEE

J. Park et al., “Faster CNNs with Direct Sparse Convolutions and Guided Pruning,” arXiv (Cornell University), 2016, doi: 10.48550/arxiv.1608.01409.

BibTeX

@misc{park2016faster,
  title     = {{Faster CNNs with Direct Sparse Convolutions and Guided Pruning}},
  author    = {Park, Jongsoo and Li, Sheng and Wen, Wei Xiong and Tang, Ping Tak Peter and Li, Hai Helen and Chen, Yiran and Dubey, Pradeep Kumar},
  howpublished = {arXiv (Cornell University)},
  year      = {2016},
  doi       = {10.48550/arxiv.1608.01409},
  url       = {https://doi.org/10.48550/arxiv.1608.01409}
}

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

Citations by year

YearCitationsShare of the best year
201733
20181818
20193434
20203131
20213535
20221919
20232222
20241616
202588
202666

Topic and keywords

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

  • sparse convolution
  • convolutional neural network pruning
  • inference acceleration
  • performance modeling
  • model compression
  • Intel processors

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?

Park, J., Li, S., Wen, W. X., Tang, P. T. P., Li, H. H., Chen, Y., & Dubey, P. K. (2016). Faster CNNs with Direct Sparse Convolutions and Guided Pruning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1608.01409

How many times has this paper been cited?

192 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?

Jongsoo Park, Sheng Li, Wei Xiong Wen, Ping Tak Peter Tang, Hai Helen Li, Yiran Chen, Pradeep Kumar Dubey.

What is the DOI of this paper?

10.48550/arxiv.1608.01409, permanently at https://doi.org/10.48550/arxiv.1608.01409. 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.