Skip to main content

Self-Adaptive Network Pruning

  • Conference paper
  • First Online:
Neural Information Processing (ICONIP 2019)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 11953))

Included in the following conference series:

Abstract

Deep convolutional neural networks have been proved successful on a wide range of tasks, yet they are still hindered by their large computation cost in many industrial scenarios. In this paper, we propose to reduce such cost for CNNs through a self-adaptive network pruning method (SANP). Our method introduces a general Saliency-and-Pruning Module (SPM) for each convolutional layer, which learns to predict saliency scores and applies pruning for each channel. Given a total computation budget, SANP adaptively determines the pruning strategy with respect to each layer and each sample, such that the average computation cost meets the budget. This design allows SANP to be more efficient in computation, as well as more robust to datasets and backbones. Extensive experiments on 2 datasets and 3 backbones show that SANP surpasses state-of-the-art methods in both classification accuracy and pruning rate.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)

    Google Scholar 

  2. Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks: training deep neural networks with weights and activations constrained to +1 or \(-1\). arXiv preprint arXiv:1602.02830 (2016)

  3. Du, S.S., Zhai, X., Poczos, B., Singh, A.: Gradient descent provably optimizes over-parameterized neural networks. In: International Conference on Learning Representations (2019)

    Google Scholar 

  4. Gao, X., Zhao, Y., Dudziak, L., Mullins, R., Xu, C.-z.: Dynamic channel pruning: feature boosting and suppression. In: International Conference on Learning Representations (2019)

    Google Scholar 

  5. Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)

    Google Scholar 

  6. Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. In: International Conference on Learning Representations (2016)

    Google Scholar 

  7. 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 

  8. Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)

    Google Scholar 

  9. Hua, W., De Sa, C., Zhang, Z., Suh, G.E.: Channel gating neural networks. In: Proceedings of the 55th Annual Design Automation Conference (2018)

    Google Scholar 

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

    Google Scholar 

  11. Kaiser, Ł., Bengio, S.: Discrete autoencoders for sequence models. arXiv preprint arXiv:1801.09797 (2018)

  12. Kaiser, Ł., Sutskever, I.: Neural gpus learn algorithms. arXiv preprint arXiv:1511.08228 (2015)

  13. Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)

    Google Scholar 

  14. 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)

    Google Scholar 

  15. Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: International Conference on Learning Representations (2017)

    Google Scholar 

  16. Lin, J., Rao, Y., Lu, J., Zhou, J.: Runtime neural pruning. In: Advances in Neural Information Processing Systems, pp. 2181–2191 (2017)

    Google Scholar 

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

    Google Scholar 

  18. Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2736–2744 (2017)

    Google Scholar 

  19. Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)

    Google Scholar 

  20. Luo, J.H., Wu, J.: Autopruner: An end-to-end trainable filter pruning method for efficient deep model inference. arXiv preprint arXiv:1805.08941 (2018)

  21. Ma, N., Zhang, X., Zheng, H.T., Sun, J.: Shufflenet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116–131 (2018)

    Chapter  Google Scholar 

  22. Micikevicius, P., et al.: Mixed precision training. In: International Conference on Learning Representations (2018)

    Google Scholar 

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

  24. Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848–6856 (2018)

    Google Scholar 

  25. Zhao, Y., Gao, X., Mullins, R., Xu, C.: Mayo: a framework for auto-generating hardware friendly deep neural networks. In: Proceedings of the 2nd International Workshop on Embedded and Mobile Deep Learning, pp. 25–30. ACM (2018)

    Google Scholar 

  26. Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., Zou, Y.: Dorefa-net: training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016)

  27. Zhou, Z., Zhou, W., Li, H., Hong, R.: Online filter clustering and pruning for efficient convnets. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 11–15. IEEE (2018)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Yuming Zhao .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chen, J., Zhu, Z., Li, C., Zhao, Y. (2019). Self-Adaptive Network Pruning. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Lecture Notes in Computer Science(), vol 11953. Springer, Cham. https://doi.org/10.1007/978-3-030-36708-4_15

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-36708-4_15

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-36707-7

  • Online ISBN: 978-3-030-36708-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics