Abstract
Channel pruning is widely used to reduce the complexity of deep network models. Recent pruning methods usually identify which parts of the network to discard by proposing a channel importance criterion. However, recent studies have shown that these criteria do not work well in all conditions. In this paper, we propose a novel Feature Shift Minimization (FSM) method to compress CNN models, which evaluates the feature shift by converging the information of both features and filters. Specifically, we first investigate the compression efficiency with some prevalent methods in different layer-depths and then propose the feature shift concept. Then, we introduce an approximation method to estimate the magnitude of the feature shift, since it is difficult to compute it directly. Besides, we present a distribution-optimization algorithm to compensate for the accuracy loss and improve the network compression efficiency. The proposed method yields state-of-the-art performance on various benchmark networks and datasets, verified by extensive experiments. Our codes are available at: https://github.com/lscgx/FSM.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K.P., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40, 834–848 (2018)
Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. arXiv abs/1802.02611 (2018)
Chin, T.W., Ding, R., Zhang, C., Marculescu, D.: Towards efficient model compression via learned global ranking. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1515–1525 (2020)
Gao, S., Huang, F., Cai, W.T., Huang, H.: Network pruning via performance maximization. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9266–9276 (2021)
Girdhar, R., Tran, D., Torresani, L., Ramanan, D.: Distinit: learning video representations without a single labeled video. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 852–861 (2019)
Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: AISTATS (2011)
Guo, J., et al.: Hit-detector: hierarchical trinity architecture search for object detection. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11402–11411 (2020)
Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural network. arXiv abs/1506.02626 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1026–1034 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
He, Y., Ding, Y., Liu, P., Zhu, L., Zhang, H., Yang, Y.: Learning filter pruning criteria for deep convolutional neural networks acceleration. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2006–2015 (2020)
He, Y., Kang, G., Dong, X., Fu, Y., Yang, Y.: Soft filter pruning for accelerating deep convolutional neural networks. arXiv abs/1808.06866 (2018)
He, Y., Liu, P., Wang, Z., Yang, Y.: Pruning filter via geometric median for deep convolutional neural networks acceleration. arXiv abs/1811.00250 (2018)
He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1398–1406 (2017)
Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv abs/1503.02531 (2015)
Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv abs/1704.04861 (2017)
Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269 (2017)
Huang, Z., Wang, N.: Data-driven sparse structure selection for deep neural networks. arXiv abs/1707.01213 (2018)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv abs/1502.03167 (2015)
Jiang, L., Xu, M., Liu, T., Qiao, M., Wang, Z.: DeepVS: a deep learning based video saliency prediction approach. In: ECCV (2018)
Kang, M., Han, B.: Operation-aware soft channel pruning using differentiable masks. In: ICML (2020)
Krizhevsky, A.: Learning multiple layers of features from tiny images (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60, 84–90 (2012)
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient convnets. arXiv abs/1608.08710 (2017)
Li, Y., Gu, S., Zhang, K., Gool, L.V., Timofte, R.: DHP: differentiable meta pruning via hypernetworks. arXiv abs/2003.13683 (2020)
Li, Y., et al.: Towards compact CNNs via collaborative compression. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6434–6443 (2021)
Lin, M., et al.: HRank: filter pruning using high-rank feature map. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1526–1535 (2020)
Lin, S., et al.: Towards optimal structured CNN pruning via generative adversarial learning. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2785–2794 (2019)
Lin, T., Liu, X., Li, X., Ding, E., Wen, S.: BMN: boundary-matching network for temporal action proposal generation. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 3888–3897 (2019)
Liu, Z., et al.: Metapruning: meta learning for automatic neural network channel pruning. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 3295–3304 (2019)
Liu, Z., Shen, Z., Savvides, M., Cheng, K.T.: Reactnet: towards precise binary neural network with generalized activation functions. arXiv abs/2003.03488 (2020)
Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2755–2763 (2017)
Luo, J.H., Wu, J., Lin, W.: ThiNet: a filter level pruning method for deep neural network compression. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5068–5076 (2017)
Oh, J., Kim, H., Baik, S., Hong, C., Lee, K.M.: Batch normalization tells you which filter is important. In: 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 3351–3360 (2022)
Paszke, A., et al.: Automatic differentiation in pytorch (2017)
Peng, H., Wu, J., Chen, S., Huang, J.: Collaborative channel pruning for deep networks. In: ICML (2019)
Raja, K.B., Raghavendra, R., Busch, C.: Obtaining stable iris codes exploiting low-rank tensor space and spatial structure aware refinement for better iris recognition. In: 2019 International Conference on Biometrics (ICB), pp. 1–8 (2019)
Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137–1149 (2015)
Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39, 640–651 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2015)
Singh, P., Verma, V.K., Rai, P., Namboodiri, V.P.: Leveraging filter correlations for deep model compression. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 824–833 (2020)
Szegedy, C., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015)
Wang, H., Qin, C., Zhang, Y., Fu, Y.: Neural pruning via growing regularization. In: International Conference on Learning Representations (2020)
Wang, Z., Li, C., Wang, X.: Convolutional neural network pruning with structural redundancy reduction. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14908–14917 (2021)
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)
Wang, Z., et al.: Model pruning based on quantified similarity of feature maps. arXiv abs/2105.06052 (2021)
You, Z., Yan, K., Ye, J., Ma, M., Wang, P.: Gate decorator: global filter pruning method for accelerating deep convolutional neural networks. arXiv abs/1909.08174 (2019)
Zhang, Y., Gao, S., Huang, H.: Exploration and estimation for model compression. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 477–486 (2021)
Zhuang, Z., et al.: Discrimination-aware channel pruning for deep neural networks. In: NeurIPS (2018)
Acknowledgements
The work was supported by National Natural Science Foundation of China (Grant Nos. 61976246 and U20A20227), Natural Science Foundation of Chongqing (Grant No. cstc2020jcyj-msxm X0385).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Duan, Y., Zhou, Y., He, P., Liu, Q., Duan, S., Hu, X. (2023). Network Pruning via Feature Shift Minimization. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13841. Springer, Cham. https://doi.org/10.1007/978-3-031-26319-4_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-26319-4_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26318-7
Online ISBN: 978-3-031-26319-4
eBook Packages: Computer ScienceComputer Science (R0)