Preprint · 2019 · Open access

26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone

Wei Niu, Xiaolong Ma, Yanzhi Wang, Bin Ren

arXiv (Cornell University) · Published 2 May 2019 · DOI 10.48550/arxiv.1905.00571

Open PDFView at the publisherCite this paper

In brief

“26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone” is a 2019 preprint by Wei Niu and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 34 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
34
Most cited in
2022 (8)
References
20
Authors
4

Abstract

With the rapid emergence of a spectrum of high-end mobile devices, many applications that required desktop-level computation capability formerly can now run on these devices without any problem. However, without a careful optimization, executing Deep Neural Networks (a key building block of the real-time video stream processing that is the foundation of many popular applications) is still challenging, specifically, if an extremely low latency or high accuracy inference is needed. This work presents CADNN, a programming framework to efficiently execute DNN on mobile devices with the help of advanced model compression (sparsity) and a set of thorough architecture-aware optimization. The evaluation result demonstrates that CADNN outperforms all the state-of-the-art dense DNN execution frameworks like TensorFlow Lite and TVM.

Cite this paper

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

APA 7

Niu, W., Ma, X., Wang, Y., & Ren, B. (2019). 26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1905.00571

MLA 9

Niu, Wei, et al. “26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone.” arXiv (Cornell University), 2019. https://doi.org/10.48550/arxiv.1905.00571.

Chicago

Niu, Wei, Xiaolong Ma, Yanzhi Wang, and Bin Ren. 2019. “26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1905.00571.

Harvard

Niu, W. et al. (2019) ‘26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone’, arXiv (Cornell University). doi:10.48550/arxiv.1905.00571.

IEEE

W. Niu, X. Ma, Y. Wang, and B. Ren, “26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone,” arXiv (Cornell University), 2019, doi: 10.48550/arxiv.1905.00571.

BibTeX

@misc{niu2019inference,
  title     = {{26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone}},
  author    = {Niu, Wei and Ma, Xiaolong and Wang, Yanzhi and Ren, Bin},
  howpublished = {arXiv (Cornell University)},
  year      = {2019},
  doi       = {10.48550/arxiv.1905.00571},
  url       = {https://doi.org/10.48550/arxiv.1905.00571}
}

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

Citations by year

YearCitationsShare of the best year
201911
202055
202177
202288
202322
202488
202522
202611

Topic and keywords

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

  • deep neural network inference
  • mobile devices
  • real-time execution
  • model compression
  • sparsity
  • ResNet50
  • low-latency inference
  • video stream processing

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?

Niu, W., Ma, X., Wang, Y., & Ren, B. (2019). 26ms Inference Time for ResNet-50: Towards Real-Time Execution of all DNNs on Smartphone. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1905.00571

How many times has this paper been cited?

34 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?

Wei Niu, Xiaolong Ma, Yanzhi Wang, Bin Ren.

What is the DOI of this paper?

10.48550/arxiv.1905.00571, permanently at https://doi.org/10.48550/arxiv.1905.00571. 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.