Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

DcaNAS: efficient convolutional network Design for Desktop CPU platforms

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

The hardware platform is a significant consideration in efficient CNN model design. Most lightweight networks are based on GPUs and mobile devices. However, they are usually not efficient nor fast enough for desktop CPU platforms. In this paper, we aim to explore the design of highly-efficient convolutional architectures for desktop CPU platforms. To achieve our goal, we first derive a series of CNN model design guidelines for CPU-based devices by comparing different computing platforms. Based on these proposed guidelines, we further present a Desktop CPU-Aware network architecture search (DcaNAS) to search for the optimal network structure with lower CPU latency. By combining automatic search and manual design, our DcaNAS achieves better flexibility and efficiency. On the ImageNet benchmark, we employ DcaNAS to produce two CPU-based lightweight CNN models: DcaNAS-L for higher accuracy and DcaNAS-S for faster speed. On a single CPU core, DcaNAS-L achieves 78.8% Top-1 (94.6% Top-5) accuracy at 13.6 FPS (73.5 ms), and our DcaNAS-S achieves extremely low CPU latency (43.1 ms). The results show that our DcaNAS method can obtain new state-of-the-art CPU-based networks.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Tan M, Pang R, Le QV (2020) EfficientDet: scalable and efficient object. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2020, pp. 10781–10790

  2. Howard A, Sandler M, Chen B et al (2019) Searching for MobileNetV3. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019, pp. 1314–1324

  3. Ma N, Zhang X, Zheng H, Sun J (2018) ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: European Conference on Computer Vision (ECCV), 2018, pp. 116–131

  4. Zhang X, Zhou X, Lin M, Sun J (2018) ShuffleNet: an extremely efficient convolutional neural network for Mobile devices. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2018, pp. 6848–6856

  5. Sandler M, Howard A, Zhu M et al (2018) MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510–4520

  6. Gennari M, Fawcett R, Prisacariu VA (2019) DSConv: efficient convolution operator. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019, pp. 5148–5157

  7. Singh P, Verma VK, Rai P, Namboodiri VP (2019) HetConv: heterogeneous kernel-based convolutions for deep CNNs. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2019, pp. 4835–4844

  8. Han K, Wang Y, Tian Q et al (2020) GhostNet: more features from cheap operations. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2020, pp. 1580–1589

  9. Wu B, Wan A, Yue X et al (2018) Shift: a zero FLOP, zero parameter alternative to spatial convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 9127–9135

  10. Radosavovic I, Kosaraju RP, Girshick R et al (2020) Designing network design spaces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 10428–10436

  11. Zoph B, Vasudevan V, Shlens J et al (2018) Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 8697–8710

  12. Yang Z, Wang Y, Chen X et al (2020) CARS: continuous evolution for efficient neural architecture search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 1829–1838

  13. Wan A, Dai X, Zhang P et al (2020) FBNetV2: differentiable neural architecture search for spatial and channel dimensions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 12965–12974

  14. Fang J, Sun Y, Zhang Q et al (2020) Densely connected search space for more flexible neural architecture search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 10628–10637

  15. Chu X, Zhang B, Li J, Li Q, Xu R (2019) SCARLET-NAS: bridging the gap between stability and scalability in weight-sharing neural architecture search. 2019 arXiv: 1908.06022. [online]. Available: http://arxiv.org/abs/1908.06022

  16. You S, Huang T, Yang M et al (2020) GreedyNAS: towards fast one-shot NAS with greedy Supernet. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 1999–2008

  17. Baker B,Gupta O, Naik N et al (2017) Designing neural network architectures using reinforcement learning. In: international conference on learning representations (ICLR), 2017

  18. Liu H, Simonyan K, Yang Y (2019) DARTS: differentiable architecture search. In: International Conference on Learning Representations (ICLR), 2019

  19. Tan M, Chen B, Pang R et al (2019) MnasNet: platform-aware neural architecture search for Mobile. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 2820–2828

  20. Bender G, Kindermans PJ, Zoph B et al (2018) Understanding and simplifying one-shot architecture search. In: proceedings of the 35th international conference on machine learning (ICML). 2018, PMLR 80:550-559

  21. Guo Z, Zhang X, Mu H et al (2020) Single path one-shot neural architecture search with uniform sampling. In: European Conference on Computer Vision (ECCV), 2020, pp. 544–560

  22. Chen Y, Yang T, Zhang X et al (2019) DetNAS: Backbone Search for Object Detection In: Conference and Workshop on Neural Information Processing Systems (NeurIPS), 2019

  23. Chu X, Zhang B, Xu R et al (2019) FairNAS: rethinking evaluation fairness of weight sharing neural architecture search. 2019 arXiv: 1907.01845. [online]. Available: http://arxiv.org/abs/1907.01845

  24. Chu X, Zhang B, Xu R (2019) Searching beyond MobileNetV3. IEEE international conference on acoustics, speech and signal processing (ICASSP). Barcelona, Spain, may, 2020

  25. Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Comput 6:182–197

    Article  Google Scholar 

  26. Howard AG, Zhu M, Chen B et al (2017) MobileNets: efficient convolutional neural networks for Mobile vision applications. 2017 arXiv: 1704.04861. [online]. Available: http://arxiv.org/abs/1704.04861

  27. Zhou D, Zhou X, Zhang W et al (2020) EcoNAS: finding proxies for economical neural architecture search. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 11396–11404

  28. Li C, Peng J, Yuan L et al (2020) Block-wisely supervised neural architecture search with knowledge distillation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 1989–1998

  29. Tan M, Le QV (2019) EfficientNet: rethinking model scaling for convolutional neural networks. 2019 arXiv: 1905.11946. [online]. Available: http://arxiv.org/abs/1905.11946

  30. Russakovsky O, Deng J, Su H et al (2015) Imagenet large scale visual recognition challenge. International journal of computer vision, 115(3):211–252, 2015

  31. Li X, Lin C, Li C et al (2020) Improving one-shot NAS by suppressing the posterior fading. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 13836–13845

  32. Cai H, Zhu L, Han S (2019) ProxylessNAS: direct neural architecture search on target task and hardware. In: International Conference on Learning Representations (ICLR), 2019

  33. Yu J, Huang T (2020) AutoSlim: towards one-shot architecture search for channel numbers. In: International Conference on Learning Representations (ICLR), 2020

  34. He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: European Conference on Computer Vision (ECCV), 2016, pp. 630–645

  35. Loshchilov I, Hutter F (2017) SGDR: stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (ICLR), 2017, pp. 6009–6025

  36. He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778

  37. Xie S, Girshick R, Dollár P et al (2017) Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1492–1500

  38. Huang G, Liu Z, Van Der Maaten L et al (2017) Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4700–4708

  39. Li Z, Peng C, Yu G et al (2018) DetNet: a backbone network for object detection. In: European Conference on Computer Vision (ECCV), 2018, pp. 334–350

  40. Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. 2018 arXiv: 1804.02767. [online]. Available: http://arxiv.org/abs/1804.02767

  41. Chollet F (2017) Xception: deep learning with Depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp.1800–1807

  42. Szegedy C, Vanhoucke V, Ioffe S et al (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 2818–2826

  43. Szegedy C, Ioffe S, Vanhoucke V et al (2017) Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning AAAI Conference on Artificial Intelligence, 2017

  44. Zhu C, Chen F, Shen Z et al (2020) Soft Anchor-Point Object Detection In: European Conference on Computer Vision (ECCV), 2020

  45. Liu S, Qi L, Qin H et al (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 8759–8768

  46. Liu W, Anguelov D, Erhan D et al (2016) SSD: single shot MultiBox detector. In: European Conference on Computer Vision (ECCV), 2016, pp. 21–37

  47. Redmon J, Farhadi A (2017) YOLO 9000: Better, Faster, Stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 7263–7271

  48. Bochkovskiy A, Wang CY, Liao HYM (2020) YOLOv4: optimal speed and accuracy of object detection. 2020 arXiv: 2004.10934. [online]. Available: http://arxiv.org/abs/2004.10934

  49. Wang RJ, Li X, Ling CX (2018) Pelee: a real-time object detection system on mobile devices. In Advances in Neural Information Processing Systems, 2018, pp.1963–1972

  50. Qin Z, Li Z, Zhang Z et al (2019) ThunderNet: towards real-time generic object detection on Mobile devices. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019, pp. 6718–6727

  51. Zhu C, He Y, Savvides M et al (2019) Feature selective anchor-free module for single-shot object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 840–849

  52. Woo S, Park J, Lee JY et al (2018) CBAM: convolutional block attention module. In: European Conference on Computer Vision (ECCV), 2018, pp. 3–19

Download references

Author information

Authors and Affiliations

  1. Communication Strategy of China Co-Innovation Center, Communication University of China, Beijing, China

    Dong Chen & Hao Shen

  2. Shared Bike and Ebike Department, Mobike Information Technology Limited, Beijing, China

    Yuchen Shen

Authors
  1. Dong Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hao Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuchen Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dong Chen.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, D., Shen, H. & Shen, Y. DcaNAS: efficient convolutional network Design for Desktop CPU platforms. Appl Intell 51, 4353–4366 (2021). https://doi.org/10.1007/s10489-020-02133-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-020-02133-0

Keywords

Search

Navigation