Accelerating Deep Convnets via Sparse Subspace Clustering

  • Dong WangEmail author
  • Shengge Shi
  • Xiao Bai
  • Xueni Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11902)


While the research on convolutional neural networks (CNNs) is progressing quickly, the real-world deployment of these models is often limited by computing resources and memory constraints. In this paper, we address this issue by proposing a novel filter pruning method to compress and accelerate CNNs. Our method reduces the redundancy in one convolutional layer by applying sparse subspace clustering to its output feature maps. In this way, most of the representative information in the network can be retained in each cluster. Therefore, our method provides an effective solution to filter pruning for which most existing methods directly remove filters based on simple heuristics. The proposed method is independent of the network structure, and thus it can be adopted by any off-the-shelf deep learning libraries. Evaluated on VGG-16 and ResNet-50 using ImageNet, our method outperforms existing techniques before fine-tuning, and achieves state-of-the-art results after fine-tuning.


Convolutional neural networks Network acceleration Filter pruning Clustering 



This work was supported by the National Natural Science Foundation of China project no. 61772057 and the support funding from State Key Lab. of Software Development Environment and Qingdao Research Institute.


  1. 1.
    Ba, J., Caruana, R.: Do deep nets really need to be deep? In: NIPS, pp. 2654–2662 (2014)Google Scholar
  2. 2.
    Denton, E.L., Zaremba, W., Bruna, J., LeCun, Y., Fergus, R.: Exploiting linear structure within convolutional networks for efficient evaluation. In: NIPS, pp. 1269–1277 (2014)Google Scholar
  3. 3.
    Elhamifar, E., Vidal, R.: Sparse subspace clustering: algorithm, theory, and applications. TPAMI 35(11), 2765–2781 (2012)CrossRefGoogle Scholar
  4. 4.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  5. 5.
    He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: ICCV, pp. 1–9 (2017)Google Scholar
  6. 6.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML, pp. 448–456 (2015)Google Scholar
  7. 7.
    Jaderberg, M., Vedaldi, A., Zisserman, A.: Speeding up convolutional neural networks with low rank expansions. In: BMVC, pp. 1–12 (2014)Google Scholar
  8. 8.
    Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: ACM MM, pp. 675–678 (2014)Google Scholar
  9. 9.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR, pp. 1–14 (2015)Google Scholar
  10. 10.
    Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: ICLR, pp. 1–13 (2017)Google Scholar
  11. 11.
    Luo, J.H., Wu, J., Lin, W.: ThiNet: a filter level pruning method for deep neural network compression. In: ICCV, pp. 1–9 (2017)Google Scholar
  12. 12.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML, pp. 807–814 (2010)Google Scholar
  13. 13.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91–99 (2015)Google Scholar
  14. 14.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR, pp. 1–13 (2015)Google Scholar
  16. 16.
    Wang, P., Cheng, J.: Accelerating convolutional neural networks for mobile applications. In: ACM MM, pp. 541–545 (2016)Google Scholar
  17. 17.
    Zhang, X., Zou, J., He, K., Sun, J.: Accelerating very deep convolutional networks for classification and detection. TPAMI 38(10), 1943–1955 (2016)CrossRefGoogle Scholar
  18. 18.
    Zhou, L., Bai, X., Liu, X., Zhou, J.: Binary coding by matrix classifier for efficient subspace retrieval. In: ICMR, pp. 82–90. ACM (2018)Google Scholar
  19. 19.
    Zhou, L., Bai, X., Wang, D., Liu, X., Zhou, J., Edwin, H.: Deep subspace clustering via latent distribution preserving. In: IJCAI, pp. 1–10 (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Computer Science and Engineering, Beijing Advanced Innovation Center for Big Data and Brain Computing, Qingdao Research InstituteBeihang UniversityBeijingChina

Personalised recommendations