Skip to main content
Springer Nature Link
Log in

Dynamic ReLU

  • Conference paper
  • First Online:
Computer Vision – ECCV 2020 (ECCV 2020)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12364))

Included in the following conference series:

  • 5286 Accesses

Abstract

Rectified linear units (ReLU) are commonly used in deep neural networks. So far ReLU and its generalizations (non-parametric or parametric) are static, performing identically for all input samples. In this paper, we propose Dynamic ReLU (DY-ReLU), a dynamic rectifier of which parameters are generated by a hyper function over all input elements. The key insight is that DY-ReLU encodes the global context into the hyper function, and adapts the piecewise linear activation function accordingly. Compared to its static counterpart, DY-ReLU has negligible extra computational cost, but significantly more representation capability, especially for light-weight neural networks. By simply using DY-ReLU for MobileNetV2, the top-1 accuracy on ImageNet classification is boosted from 72.0% to 76.2% with only 5% additional FLOPs.

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

Access this chapter

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

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Cai, H., Gan, C., Han, S.: Once for all: train one network and specialize it for efficient deployment. arXiv:abs/1908.09791 (2019)

  2. Cai, H., Zhu, L., Han, S.: ProxylessNAS: direct neural architecture search on target task and hardware. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=HylVB3AqYm

  3. Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., Liu, Z.: Dynamic convolution: attention over convolution kernels. arXiv:abs/1912.03458 (2019)

  4. Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUS). arXiv preprint arXiv:1511.07289 (2015)

  5. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)

    Google Scholar 

  6. Dugas, C., Bengio, Y., Bélisle, F., Nadeau, C., Garcia, R.: Incorporating second-order functional knowledge for better option pricing. In: Advances in Neural Information Processing Systems, pp. 472–478 (2001)

    Google Scholar 

  7. Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. arXiv preprint arXiv:1302.4389 (2013)

  8. Ha, D., Dai, A.M., Le, Q.V.: Hypernetworks. In: ICLR (2017)

    Google Scholar 

  9. Hahnloser, R.H., Sarpeshkar, R., Mahowald, M.A., Douglas, R.J., Seung, H.S.: Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature 405(6789), 947–951 (2000)

    Article  Google Scholar 

  10. He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: ICCV (2015)

    Google Scholar 

  11. 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)

    Google Scholar 

  12. Howard, A., et al.: Searching for MobileNetv3. CoRR abs/1905.02244 (2019). http://arxiv.org/abs/1905.02244

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

  14. Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018

    Google Scholar 

  15. Huang, G., Chen, D., Li, T., Wu, F., van der Maaten, L., Weinberger, K.: Multi-scale dense networks for resource efficient image classification. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=Hk2aImxAb

  16. Iandola, F.N., Moskewicz, M.W., Ashraf, K., Han, S., Dally, W.J., Keutzer, K.: SqueezeNet: alexnet-level accuracy with 50\(\times \) fewer parameters and \(<\)1 mb model size. CoRR abs/1602.07360 (2016). http://arxiv.org/abs/1602.07360

  17. Jarrett, K., Kavukcuoglu, K., Ranzato, M., LeCun, Y.: What is the best multi-stage architecture for object recognition? In: The IEEE International Conference on Computer Vision (ICCV) (2009)

    Google Scholar 

  18. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015)

    Google Scholar 

  19. Klambauer, G., Unterthiner, T., Mayr, A., Hochreiter, S.: Self-normalizing neural networks. In: Advances in Neural Information Processing Systems, pp. 971–980 (2017)

    Google Scholar 

  20. Lin, J., Rao, Y., Lu, J., Zhou, J.: Runtime neural pruning. In: Advances in Neural Information Processing Systems, pp. 2181–2191 (2017). http://papers.nips.cc/paper/6813-runtime-neural-pruning.pdf

  21. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48

    Chapter  Google Scholar 

  22. Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=S1eYHoC5FX

  23. Liu, L., Deng, J.: Dynamic deep neural networks: optimizing accuracy-efficiency trade-offs by selective execution. In: AAAI Conference on Artificial Intelligence (AAAI) (2018)

    Google Scholar 

  24. Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 122–138. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_8

    Chapter  Google Scholar 

  25. Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: in ICML Workshop on Deep Learning for Audio, Speech and Language Processing (2013)

    Google Scholar 

  26. Misra, D.: Mish: a self regularized non-monotonic neural activation function. arXiv preprint arXiv:1908.08681 (2019)

  27. Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML (2010)

    Google Scholar 

  28. Ramachandran, P., Zoph, B., Le, Q.V.: Searching for activation functions. arXiv preprint arXiv:1710.05941 (2017)

  29. Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: AAAI Conference on Artificial Intelligence (AAAI) (2018)

    Google Scholar 

  30. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)

    Google Scholar 

  31. Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR (2019)

    Google Scholar 

  32. Tan, M., et al.: MnasNet: platform-aware neural architecture search for mobile. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019

    Google Scholar 

  33. Trottier, L., Gigu, P., Chaib-draa, B., et al.: Parametric exponential linear unit for deep convolutional neural networks. In: 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 207–214. IEEE (2017)

    Google Scholar 

  34. Wang, X., Yu, F., Dou, Z.-Y., Darrell, T., Gonzalez, J.E.: SkipNet: learning dynamic routing in convolutional networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 420–436. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01261-8_25

    Chapter  Google Scholar 

  35. Wu, B., et al.: FBNet: hardware-aware efficient convnet design via differentiable neural architecture search. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019

    Google Scholar 

  36. Wu, B., et al.: Shift: a zero flop, zero parameter alternative to spatial convolutions (2017)

    Google Scholar 

  37. Wu, Z., et al.: BlockDrop: dynamic inference paths in residual networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018

    Google Scholar 

  38. Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 472–487. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_29

    Chapter  Google Scholar 

  39. Xie, S., Zheng, H., Liu, C., Lin, L.: SNAS: stochastic neural architecture search. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=rylqooRqK7

  40. Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. CoRR (2015)

    Google Scholar 

  41. Yang, B., Bender, G., Le, Q.V., Ngiam, J.: CondConv: conditionally parameterized convolutions for efficient inference. In: NeurIPS (2019)

    Google Scholar 

  42. Yu, J., Yang, L., Xu, N., Yang, J., Huang, T.: Slimmable neural networks. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=H1gMCsAqY7

  43. Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=r1Ddp1-Rb

  44. Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018

    Google Scholar 

  45. Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. CoRR abs/1611.01578 (2017)

    Google Scholar 

  46. Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Microsoft Corporation, Redmond, WA, 98052, USA

    Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Lu Yuan & Zicheng Liu

Authors
  1. Yinpeng Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiyang Dai
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mengchen Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Dongdong Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Lu Yuan
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zicheng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yinpeng Chen .

Editor information

Editors and Affiliations

  1. University of Oxford, Oxford, UK

    Andrea Vedaldi

  2. Graz University of Technology, Graz, Austria

    Horst Bischof

  3. University of Freiburg, Freiburg im Breisgau, Germany

    Thomas Brox

  4. University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

    Jan-Michael Frahm

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 451 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., Liu, Z. (2020). Dynamic ReLU. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12364. Springer, Cham. https://doi.org/10.1007/978-3-030-58529-7_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-58529-7_21

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-58528-0

  • Online ISBN: 978-3-030-58529-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics