Article

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Authors:

Jian SunAuthors Info & Claims

Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part XIV

Pages 122 - 138

https://doi.org/10.1007/978-3-030-01264-9_8

Published: 08 September 2018 Publication History

Abstract

Currently, the neural network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical guidelines for efficient network design. Accordingly, a new architecture is presented, called ShuffleNet V2. Comprehensive ablation experiments verify that our model is the state-of-the-art in terms of speed and accuracy tradeoff.

References

[1]

Chetlur, S., et al.: CUDNN: efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014)

[2]

Chollet, F.: Xception: deep learning with depthwise separable convolutions. arXiv preprint (2016)

[3]

Das, D., et al.: Distributed deep learning using synchronous stochastic gradient descent. arXiv preprint arXiv:1602.06709 (2016)

[4]

Deng, J., et al.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp. 248–255. IEEE (2009)

[5]

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

[6]

He K, Zhang X, Ren S, and Sun J Leibe B, Matas J, Sebe N, and Welling M Identity mappings in deep residual networks Computer Vision – ECCV 2016 2016 Cham Springer 630-645

[7]

He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: International Conference on Computer Vision (ICCV), vol. 2, p. 6 (2017)

[8]

Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)

[9]

Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. arXiv preprint arXiv:1709.01507 (2017)

[10]

Huang, G., Liu, S., van der Maaten, L., Weinberger, K.Q.: Condensenet: an efficient densenet using learned group convolutions. arXiv preprint arXiv:1711.09224 (2017)

[11]

Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, p. 3 (2017)

[12]

Ioannou, Y., Robertson, D., Cipolla, R., Criminisi, A.: Deep roots: improving CNN efficiency with hierarchical filter groups. arXiv preprint arXiv:1605.06489 (2016)

[13]

Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456 (2015)

[14]

Jaderberg, M., Vedaldi, A., Zisserman, A.: Speeding up convolutional neural networks with low rank expansions. arXiv preprint arXiv:1405.3866 (2014)

[15]

Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)

[16]

Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., Sun, J.: Light-head R-CNN: In defense of two-stage object detector. arXiv preprint arXiv:1711.07264 (2017)

[17]

Lin T-Y et al. Fleet D, Pajdla T, Schiele B, Tuytelaars T, et al. Microsoft COCO: common objects in context Computer Vision – ECCV 2014 2014 Cham Springer 740-755

[18]

Liu, C., et al.: Progressive neural architecture search. arXiv preprint arXiv:1712.00559 (2017)

[19]

Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2755–2763. IEEE (2017)

[20]

Peng, C., Zhang, X., Yu, G., Luo, G., Sun, J.: Large kernel matters-improve semantic segmentation by global convolutional network. arXiv preprint arXiv:1703.02719 (2017)

[21]

Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. arXiv preprint arXiv:1802.01548 (2018)

[22]

Real, E., et al.: Large-scale evolution of image classifiers. arXiv preprint arXiv:1703.01041 (2017)

[23]

Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, and Bernstein M Imagenet large scale visual recognition challenge Int. J. Comput. Vis. 2015 115 3 211-252

[24]

Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Inverted residuals and linear bottlenecks: mobile networks for classification, detection and segmentation. arXiv preprint arXiv:1801.04381 (2018)

[25]

Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)

[26]

Sun, K., Li, M., Liu, D., Wang, J.: Igcv 3: Interleaved low-rank group convolutions for efficient deep neural networks. arXiv preprint arXiv:1806.00178 (2018)

[27]

Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI, vol. 4, p. 12 (2017)

[28]

Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)

[29]

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

[30]

Wen, W., Wu, C., Wang, Y., Chen, Y., Li, H.: Learning structured sparsity in deep neural networks. In: Advances in Neural Information Processing Systems, pp. 2074–2082 (2016)

[31]

Xie, G., Wang, J., Zhang, T., Lai, J., Hong, R., Qi, G.J.: IGCV

2

: Interleaved structured sparse convolutional neural networks. arXiv preprint arXiv:1804.06202 (2018)

[32]

Xie, L., Yuille, A.: Genetic CNN. arXiv preprint arXiv:1703.01513 (2017)

[33]

Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5987–5995. IEEE (2017)

[34]

Zhang, T., Qi, G.J., Xiao, B., Wang, J.: Interleaved group convolutions for deep neural networks. In: International Conference on Computer Vision (2017)

[35]

Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. arXiv preprint arXiv:1707.01083 (2017)

[36]

Zhang X, Zou J, He K, and Sun J Accelerating very deep convolutional networks for classification and detection IEEE Trans. Pattern Anal. Mach. Intell. 2016 38 10 1943-1955

[37]

Zhang, X., Zou, J., Ming, X., He, K., Sun, J.: Efficient and accurate approximations of nonlinear convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1984–1992 (2015)

[38]

Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)

[39]

Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. arXiv preprint arXiv:1707.07012 (2017)

Cited By

Li GLi RLi TChen TZhang MCorporaal H(2025)Algorithm-Hardware Co-design for Accelerating Depthwise Separable CNNsACM Transactions on Design Automation of Electronic Systems10.1145/3711846Online publication date: 9-Jan-2025
https://dl.acm.org/doi/10.1145/3711846
Liu QYu YHan BZhou W(2025)An evolutionary deep learning approach using flexible variable-length dynamic stochastic search for anomaly detection of robot jointsApplied Soft Computing10.1016/j.asoc.2024.112493168:COnline publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1016/j.asoc.2024.112493
Yue ZLi XZhou HWang GWang W(2025)Real-time recognition method for PCB chip targets based on YOLO-GSGJournal of Real-Time Image Processing10.1007/s11554-024-01616-422:1Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1007/s11554-024-01616-4
Show More Cited By

Index Terms

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Index terms have been assigned to the content through auto-classification.

Recommendations

Architectural design decision visualization for architecture design: preliminary results of a controlled experiment
ECSA '11: Proceedings of the 5th European Conference on Software Architecture: Companion Volume

Visualization of architectural design decision (ADD) and its rationale, as a kind of traceability information, is supposed to facilitate the understanding of architecture design and the reasoning behind the design rationale, which is supposed to improve ...
Software Architecture Design Assistants Need Controlled Efficiency Experiments: Lessons Learned from a Survey
FoSADA '15: Proceedings of the 1st International Workshop on Future of Software Architecture Design Assistants

Software architects use so-called software architecture design assistants to get tool-based, (semi-)automated support in engineering software systems. Compared to manual engineering, the main promise of such a support is that architects can create high-...
Guidelines for Error Message Design

The presented study aims to develop a set of guidelines for error message design. A large amount of research is available in the literature on the topic of warning design. The same is not true for error messages. Although some research exists, the ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part XIV

Sep 2018

844 pages

ISBN:978-3-030-01263-2

DOI:10.1007/978-3-030-01264-9

Editors:
Vittorio Ferrari
Google Research, Zurich, Switzerland
,
Martial Hebert
Carnegie Mellon University, Pittsburgh, PA, USA
,
Cristian Sminchisescu
Google Research, Zurich, Switzerland
,
Yair Weiss
Hebrew University of Jerusalem, Jerusalem, Israel

© Springer Nature Switzerland AG 2018.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 08 September 2018

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

340
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 02 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Li GLi RLi TChen TZhang MCorporaal H(2025)Algorithm-Hardware Co-design for Accelerating Depthwise Separable CNNsACM Transactions on Design Automation of Electronic Systems10.1145/3711846Online publication date: 9-Jan-2025
https://dl.acm.org/doi/10.1145/3711846
Liu QYu YHan BZhou W(2025)An evolutionary deep learning approach using flexible variable-length dynamic stochastic search for anomaly detection of robot jointsApplied Soft Computing10.1016/j.asoc.2024.112493168:COnline publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1016/j.asoc.2024.112493
Yue ZLi XZhou HWang GWang W(2025)Real-time recognition method for PCB chip targets based on YOLO-GSGJournal of Real-Time Image Processing10.1007/s11554-024-01616-422:1Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1007/s11554-024-01616-4
Zhang HQi YChen HCao PLiang AWen S(2025)LSDNet: lightweight stochastic depth network for human pose estimationThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-024-03323-441:1(257-270)Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1007/s00371-024-03323-4
Xu SWang MLi YLin MZhang BDoermann DSun XSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Learning 1-bit tiny object detector with discriminative feature refinementProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694351(55337-55347)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3694351
Xie LLin MLuan TLi CFang YShen QWu ZSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)MH-pFLIDProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694314(54561-54575)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3694314
Wang JZhao CLyu LYou QHuai MMa FSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Bridging model heterogeneity in federated learning via uncertainty-based asymmetrical reciprocity learningProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694213(52290-52308)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3694213
Kwon YLi RVenieris SChauhan JLane NMascolo CSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)TinyTrainProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693103(25812-25843)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3693103
Kim JYou JLee DKim HJung JSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Do topological characteristics help in knowledge distillation?Proceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693058(24674-24693)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3693058
Gala JXie PSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Leverage class-specific accuracy to guide data generation for improving image classificationProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3692647(14433-14452)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3692647
Show More Cited By

View Options

View options

Figures

Tables

Media

View Table of Conten