Skip to main content
SpringerLink
Log in

Learning Internal Dense But External Sparse Structures of Deep Convolutional Neural Network

  • Conference paper
  • First Online:
Artificial Neural Networks and Machine Learning – ICANN 2019: Deep Learning (ICANN 2019)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 11728))

Included in the following conference series:

Abstract

Recent years have witnessed two seemingly opposite developments of deep convolutional neural networks (CNNs). On the one hand, increasing the density of CNNs (e.g., by adding cross-layer connections) achieves better performance on basic computer vision tasks. On the other hand, creating sparsity structures (e.g., through pruning methods) achieves a more slim network structure. Inspired by modularity structures in the human brain, we bridge these two trends by proposing a new network structure with internally dense yet externally sparse connections. Experimental results demonstrate that our new structure could obtain competitive performance on benchmark tasks (CIFAR10, CIFAR100, and ImageNet) while keeping the network structure slim.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
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. Angeline, P.J., Pollack, J.: Evolutionary module acquisition. In: Proceedings of the Second Annual Conference on Evolutionary Programming, pp. 154–163. Citeseer (1993). https://doi.org/10.1007/978-3-540-24650-3_17

    Google Scholar 

  2. Belliveau, J., et al.: Functional mapping of the human visual cortex by magnetic resonance imaging. Science 254(5032), 716–719 (1991). https://doi.org/10.1126/science.1948051

    Article  Google Scholar 

  3. Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Networks 5(2), 157–166 (1994). https://doi.org/10.1109/72.279181

    Article  Google Scholar 

  4. Betzel, R.F., et al.: The modular organization of human anatomical brain networks: accounting for the cost of wiring. Netw. Neurosci. 1(1), 42–68 (2017). https://doi.org/10.1162/NETN_a_00002

    Article  Google Scholar 

  5. Braun, H., Weisbrod, J.: Evolving neural feedforward networks. In: Albrecht, R.F., Reeves, C.R., Steele, N.C. (eds.) Artificial Neural Nets and Genetic Algorithms, pp. 25–32. Springer, Vienna (1993). https://doi.org/10.1007/978-3-7091-7533-0_5. https://doi.org/10.1109/72.80206

    Chapter  Google Scholar 

  6. Chollet, F.: Xception: deep learning with depthwise separable convolutions. arXiv preprint, pp. 1610–02357 (2017). https://doi.org/10.1109/CVPR.2017.195

  7. 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)

  8. Denton, E.L., Zaremba, W., Bruna, J., LeCun, Y., Fergus, R.: Exploiting linear structure within convolutional networks for efficient evaluation. In: Advances in Neural Information Processing Systems, pp. 1269–1277 (2014)

    Google Scholar 

  9. Gazzaniga, M.S.: Brain modularity: towards a philosophy of conscious experience (1988)

    Google Scholar 

  10. Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv preprint arXiv:1510.00149 (2015). https://doi.org/10.1145/2351676.2351678

  11. Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems, pp. 1135–1143 (2015)

    Google Scholar 

  12. 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). https://doi.org/10.1109/CVPR.2016.90

  13. He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38

    Chapter  Google Scholar 

  14. 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)

    Google Scholar 

  15. 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). https://doi.org/10.1109/CVPR.2017.243

  16. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)

  17. Kim, Y.D., Park, E., Yoo, S., Choi, T., Yang, L., Shin, D.: Compression of deep convolutional neural networks for fast and low power mobile applications. arXiv preprint arXiv:1511.06530 (2015)

  18. 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). https://doi.org/10.1145/3065386

    Article  Google Scholar 

  19. Larsson, G., Maire, M., Shakhnarovich, G.: FractalNet: ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648 (2016)

  20. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998). https://doi.org/10.1109/5.726791

    Article  Google Scholar 

  21. Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)

  22. Mao, H., et al.: Exploring the regularity of sparse structure in convolutional neural networks. arXiv preprint arXiv:1705.08922 (2017)

  23. Park, J., et al.: Faster CNNs with direct sparse convolutions and guided pruning. arXiv preprint arXiv:1608.01409 (2016)

  24. Pujol, J.C.F., Poli, R.: Evolving the topology and the weights of neural networks using a dual representation. Appl. Intell. 8(1), 73–84 (1998). https://doi.org/10.1023/a:1008272615525

    Article  Google Scholar 

  25. Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: ImageNet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525–542. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_32

    Chapter  Google Scholar 

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

  27. Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)

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

  29. Srinivas, M., Patnaik, L.M.: Genetic algorithms: a survey. Computer 27(6), 17–26 (1994). https://doi.org/10.1109/2.294849

    Article  Google Scholar 

  30. Srivastava, R.K., Greff, K., Schmidhuber, J.: Highway networks. arXiv preprint arXiv:1505.00387 (2015)

  31. Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002). https://doi.org/10.1162/106365602320169811

    Article  Google Scholar 

  32. 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)

    Google Scholar 

  33. 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). https://doi.org/10.1109/CVPR.2016.308

  34. Sztarker, J., Tomsic, D.: Brain modularity in arthropods: individual neurons that support “what” but not “where” memories. J. Neurosci. 31(22), 8175–8180 (2011). https://doi.org/10.1523/jneurosci.6029-10.2011

    Article  Google Scholar 

  35. Wang, J., Wei, Z., Zhang, T., Zeng, W.: Deeply-fused nets. arXiv preprint arXiv:1605.07716 (2016)

  36. 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)

    Google Scholar 

  37. 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). https://doi.org/10.1109/CVPR.2018.00922

  38. Xie, L., Yuille, A.: Genetic CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1379–1388 (2017)

    Google Scholar 

  39. Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016). https://doi.org/10.5244/C.30.87

  40. Zhou, A., Yao, A., Guo, Y., Xu, L., Chen, Y.: Incremental network quantization: towards lossless CNNs with low-precision weights. arXiv preprint arXiv:1702.03044 (2017)

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

    Google Scholar 

Download references

Acknowledgment

We thank the anonymous reviewers for their comments. This work was supported by Mitacs Accelerate Grant IT08175 with Two Hat Security Research Corporation. Part of this work has been prototyped in the CEASE.ai project at Two Hat Security.

Author information

Authors and Affiliations

  1. School of Engineering, The University of British Columbia (Okanagan Campus), Kelowna, BC, V1V 1V7, Canada

    Yiqun Duan & Chen Feng

Authors
  1. Yiqun Duan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chen Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yiqun Duan .

Editor information

Editors and Affiliations

  1. Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH), Neuherberg, Germany

    Igor V. Tetko

  2. Institute of Computer Science, Czech Academy of Sciences, Prague 8, Czech Republic

    Věra Kůrková

  3. Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH), Neuherberg, Germany

    Pavel Karpov

  4. Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH), Neuherberg, Germany

    Fabian Theis

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

Duan, Y., Feng, C. (2019). Learning Internal Dense But External Sparse Structures of Deep Convolutional Neural Network. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Deep Learning. ICANN 2019. Lecture Notes in Computer Science(), vol 11728. Springer, Cham. https://doi.org/10.1007/978-3-030-30484-3_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-30484-3_21

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-30483-6

  • Online ISBN: 978-3-030-30484-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation