Skip to main content

Disentangled Differentiable Network Pruning

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Abstract

In this paper, we propose a novel channel pruning method for compression and acceleration of Convolutional Neural Networks (CNNs). Many existing channel pruning works try to discover compact sub-networks by optimizing a regularized loss function through differentiable operations. Usually, a learnable parameter is used to characterize each channel, which entangles the width and channel importance. In this setting, the FLOPs or parameter constraints implicitly restrict the search space of the pruned model. To solve the aforementioned problems, we propose optimizing each layer’s width by relaxing the hard equality constraint used in previous works. The relaxation is inspired by the definition of the top-k operation. By doing so, we partially disentangle the learning of width and channel importance, which enables independent parametrization for width and importance and makes pruning more flexible. We also introduce soft top-k to improve the learning of width. Moreover, to make pruning more efficient, we use two neural networks to parameterize the importance and width. The importance generation network considers both inter-channel and inter-layer relationships. The width generation network has similar functions. In addition, our method can be easily optimized by popular SGD methods, which enjoys the benefits of differentiable pruning. Extensive experiments on CIFAR-10 and ImageNet show that our method is competitive with state-of-the-art methods.

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

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /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
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
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

Similar content being viewed by others

References

  1. Bengio, Y., Léonard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)

  2. Bojarski, M., et al.: End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016)

  3. Chin, T.W., Ding, R., Zhang, C., Marculescu, D.: Towards efficient model compression via learned global ranking. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1518–1528 (2020)

    Google Scholar 

  4. Cho, K., van Merrienboer, B., Gulcehre, C., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Conference on Empirical Methods in Natural Language Processing (EMNLP 2014) (2014)

    Google Scholar 

  5. Courbariaux, M., Bengio, Y., David, J.P.: Binaryconnect: training deep neural networks with binary weights during propagations. In: Advances in Neural Information Processing Systems, pp. 3123–3131 (2015)

    Google Scholar 

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

    Google Scholar 

  7. Frankle, J., Carbin, M.: The lottery ticket hypothesis: finding sparse, trainable neural networks. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=rJl-b3RcF7

  8. Ganjdanesh, A., Gao, S., Huang, H.: Interpretations steered network pruning via amortized inferred saliency maps. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)

    Google Scholar 

  9. Gao, S., Huang, F., Pei, J., Huang, H.: Discrete model compression with resource constraint for deep neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1899–1908 (2020)

    Google Scholar 

  10. Guo, J., Ouyang, W., Xu, D.: Multi-dimensional pruning: a unified framework for model compression. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1508–1517 (2020)

    Google Scholar 

  11. 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)

  12. 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 

  13. Hazimeh, H., Ponomareva, N., Mol, P., Tan, Z., Mazumder, R.: The tree ensemble layer: differentiability meets conditional computation. In: International Conference on Machine Learning, pp. 4138–4148. PMLR (2020)

    Google Scholar 

  14. 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 

  15. He, Y., Kang, G., Dong, X., Fu, Y., Yang, Y.: Soft filter pruning for accelerating deep convolutional neural networks. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 2234–2240 (2018)

    Google Scholar 

  16. He, Y., Liu, P., Wang, Z., Hu, Z., Yang, Y.: Filter pruning via geometric median for deep convolutional neural networks acceleration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4340–4349 (2019)

    Google Scholar 

  17. He, Y., Lin, J., Liu, Z., Wang, H., Li, L.J., Han, S.: AMC: Automl for model compression and acceleration on mobile devices. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 784–800 (2018)

    Google Scholar 

  18. Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)

  19. Howard, A., et al.: Searching for mobilenetv3. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1314–1324 (2019)

    Google Scholar 

  20. 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 

  21. Huang, Z., Wang, N.: Data-driven sparse structure selection for deep neural networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 304–320 (2018)

    Google Scholar 

  22. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, ICML, vol. 37, pp. 448–456. JMLR.org (2015). https://dl.acm.org/citation.cfm?id=3045118.3045167

  23. Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)

  24. Kang, M., Han, B.: Operation-aware soft channel pruning using differentiable masks. In: International Conference on Machine Learning, pp. 5122–5131. PMLR (2020)

    Google Scholar 

  25. Kim, J., Park, C., Jung, H., Choe, Y.: Plug-in, trainable gate for streamlining arbitrary neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence (2020)

    Google Scholar 

  26. Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

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

    Google Scholar 

  28. 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 

  29. Lee, N., Ajanthan, T., Torr, P.H.: Snip: single-shot network pruning based on connection sensitivity. In: ICLR (2019)

    Google Scholar 

  30. Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. In: ICLR (2017)

    Google Scholar 

  31. Li, Y., et al.: Towards compact CNNs via collaborative compression. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6438–6447 (2021)

    Google Scholar 

  32. Lin, M., et al.: Hrank: filter pruning using high-rank feature map. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    Google Scholar 

  33. Liu, Z., et al.: Metapruning: meta learning for automatic neural network channel pruning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3296–3305 (2019)

    Google Scholar 

  34. Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: ICCV (2017)

    Google Scholar 

  35. Liu, Z., Sun, M., Zhou, T., Huang, G., Darrell, T.: Rethinking the value of network pruning. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=rJlnB3C5Ym

  36. Louizos, C., Welling, M., Kingma, D.P.: Learning sparse neural networks through \(l_0\) regularization. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=H1Y8hhg0b

  37. Molchanov, D., Ashukha, A., Vetrov, D.: Variational dropout sparsifies deep neural networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70. pp. 2498–2507. JMLR.org (2017)

    Google Scholar 

  38. Molchanov, P., Mallya, A., Tyree, S., Frosio, I., Kautz, J.: Importance estimation for neural network pruning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 11264–11272 (2019)

    Google Scholar 

  39. Neklyudov, K., Molchanov, D., Ashukha, A., Vetrov, D.P.: Structured Bayesian pruning via log-normal multiplicative noise. In: Advances in Neural Information Processing Systems, pp. 6775–6784 (2017)

    Google Scholar 

  40. Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024–8035 (2019)

    Google Scholar 

  41. Peng, H., Wu, J., Chen, S., Huang, J.: Collaborative channel pruning for deep networks. In: International Conference on Machine Learning, pp. 5113–5122 (2019)

    Google Scholar 

  42. 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 

  43. Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)

    Google Scholar 

  44. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)

    Google Scholar 

  45. 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 

  46. Sehwag, V., Wang, S., Mittal, P., Jana, S.: Hydra: pruning adversarially robust neural networks. In: NeurIPS (2020). https://proceedings.neurips.cc/paper/2020/hash/e3a72c791a69f87b05ea7742e04430ed-Abstract.html

  47. Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568–576 (2014)

    Google Scholar 

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

  49. Tang, Y., et al.: SCOP: scientific control for reliable neural network pruning. In: Advances in Neural Information Processing Systems, vol. 33 (2020)

    Google Scholar 

  50. Wang, H., Qin, C., Zhang, Y., Fu, Y.: Neural pruning via growing regularization. In: International Conference on Learning Representations (2021). https://openreview.net/forum?id=o966_Is_nPA

  51. Wang, Z., Li, C., Wang, X.: Convolutional neural network pruning with structural redundancy reduction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14913–14922 (2021)

    Google Scholar 

  52. 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 

  53. Ye, M., Gong, C., Nie, L., Zhou, D., Klivans, A., Liu, Q.: Good subnetworks provably exist: pruning via greedy forward selection. In: International Conference on Machine Learning, pp. 10820–10830. PMLR (2020)

    Google Scholar 

  54. You, Z., Yan, K., Ye, J., Ma, M., Wang, P.: Gate decorator: global filter pruning method for accelerating deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 2130–2141 (2019)

    Google Scholar 

  55. Yu, S., Mazaheri, A., Jannesari, A.: Auto graph encoder-decoder for neural network pruning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6362–6372 (2021)

    Google Scholar 

  56. Zhang, D., Wang, H., Figueiredo, M., Balzano, L.: Learning to share: simultaneous parameter tying and sparsification in deep learning (2018)

    Google Scholar 

  57. Zhang, Y., Gao, S., Huang, H.: Exploration and estimation for model compression. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 487–496 (2021)

    Google Scholar 

  58. Zhang, Y., Gao, S., Huang, H.: Recover fair deep classification models via altering pre-trained structure. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)

    Google Scholar 

  59. Zhuang, Z., et al.: Discrimination-aware channel pruning for deep neural networks. In: Advances in Neural Information Processing Systems, pp. 875–886 (2018)

    Google Scholar 

Download references

Acknowledgement

This work was partially supported by NSF IIS 1845666, 1852606, 1838627, 1837956, 1956002, 2217003.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Heng Huang .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 411 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Gao, S., Huang, F., Zhang, Y., Huang, H. (2022). Disentangled Differentiable Network Pruning. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13671. Springer, Cham. https://doi.org/10.1007/978-3-031-20083-0_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20083-0_20

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20082-3

  • Online ISBN: 978-3-031-20083-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics