Abstract
The application of convolutional neural networks (CNNs) in computer vision highly depends on the consumption of computation and memory resources, which affects its development on resource-limited devices. Accordingly, CNN compression has attracted increasing attention. In this paper, we propose an efficient end-to-end pruning method based on feature stabilization (EPFS), which is feasible to be implemented for structured pruning such as filter pruning and block pruning. For block pruning, we introduce a mask to scale the output of structures and the \(\ell _1\)-regularization term to sparsify the mask. For filter pruning, a novel \(\ell _2\)-regularization term is proposed to constraint the mask along with the \(\ell _1\)-regularization. Besides, we introduce the Center Loss to stabilize the deep feature and fast iterative shrinkage-thresholding algorithm (FISTA) to accelerate the convergence of mask. Extensive experiments demonstrate the superiority of our EPFS. On CIFAR-10, EPFS saves \(47.5\%\) FLOPs on VGGNet with \(1.17\%\) Top-1 accuracy increase. Furthermore, on ImageNet ILSVRC2012, EPFS reduces \(55.2\%\) FLOPs on ResNet-18 with o.nly \(1.63\%\) Top-1 accuracy decrease, which promotes the state-of-the-arts.
Similar content being viewed by others
Notes
The number of floating-point operations.
References
Beck A, Teboulle M (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J Imaging Sci 2(1):183–202
Denil M, Shakibi B, Dinh L, Ranzato M, De Freitas N (2013) Predicting parameters in deep learning. In: Advances in neural information processing systems (NIPS), pp 2148–2156
Ding X, Ding G, Guo Y, Han J (2019) Centripetal sgd for pruning very deep convolutional networks with complicated structure. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 4943–4953
Dong X, Huang J, Yang Y, Yan S (2017) More is less: A more complicated network with less inference complexity. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 5840–5848
Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303–338
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 580–587
Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: International conference on artificial intelligence and statistics (AISTATS), pp 315–323
Goldstein T, Studer C, Baraniuk R (2014) A field guide to forward-backward splitting with a fasta implementation. arXiv preprint arXiv:1411.3406
Gu J, Li C, Zhang B, Han J, Cao X, Liu J, Doermann D (2019) Projection convolutional neural networks for 1-bit cnns via discrete back propagation. In: AAAI conference on artificial intelligence (AAAI) vol 33, pp 8344–8351
Gu J, Zhao J, Jiang X, Zhang B, Liu J, Guo G, Ji R (2019) Bayesian optimized 1-bit cnns. In: IEEE international conference on computer vision (ICCV), pp 4909–4917
Han S, Pool J, Tran J, Dally W (2015) Learning both weights and connections for efficient neural network. In: Advances in neural information processing systems (NIPS), pp 1135–1143
Hassibi B, Stork DG, Wolff GJ (1993) Optimal brain surgeon and general network pruning. In: IEEE international conference on neural networks (ICNN), pp 293–299
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778
He Y, Kang G, Dong X, Fu Y, Yang Y (2018) Soft filter pruning for accelerating deep convolutional neural networks. In: International joint conference on artificial intelligence (IJCAI), pp 2234–2240
He Y, Liu P, Wang Z, Hu Z, Yang Y (2019) Filter pruning via geometric median for deep convolutional neural networks acceleration. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 4340–4349
He Y, Zhang X, Sun J (2017) Channel pruning for accelerating very deep neural networks. In: IEEE International conference on computer vision (ICCV), pp 1389–1397
Howard A, Sandler M, Chu G, Chen LC, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V, et al (2019) Searching for mobilenetv3. In: IEEE international conference on computer vision (ICCV), pp 1314–1324
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861
Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning (ICML), pp 448–456
Krizhevsky A, Hinton G et al (2009) Learning multiple layers of features from tiny images. Tech. rep, Citeseer
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems (NIPS), pp 1097–1105
LeCun Y, Denker JS, Solla SA (1990) Optimal brain damage. In: Advances in neural information processing systems (NIPS), pp 598–605
Li H, Kadav A, Durdanovic I, Samet H, Graf HP (2017) Pruning filters for efficient convnets. In: International conference on learning representations (ICLR), pp 1–13
Lin S, Ji R, Chen C, Huang F (2017) Espace: Accelerating convolutional neural networks via eliminating spatial and channel redundancy. In: AAAI conference on artificial intelligence (AAAI), pp 1424–1430
Lin S, Ji R, Li Y, Wu Y, Huang F, Zhang B (2018) Accelerating convolutional networks via global & dynamic filter pruning. In: International joint conference on artificial intelligence (IJCAI), pp 2425–2432
Lin S, Ji R, Yan C, Zhang B, Cao L, Ye Q, Huang F, Doermann D (2019) Towards optimal structured cnn pruning via generative adversarial learning. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 2790–2799
Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European conference on computer vision (ECCV), pp 740–755
Luan S, Chen C, Zhang B, Han J, Liu J (2018) Gabor convolutional networks. IEEE Trans Image Process 27(9):4357–4366
Luo JH, Wu J, Lin W (2017) Thinet: A filter level pruning method for deep neural network compression. In: IEEE international conference on computer vision (ICCV), pp 5058–5066
Mathieu M, Henaff M, LeCun Y (2014) Fast training of convolutional networks through ffts. In: International conference on learning representations (ICLR), pp 1–9
Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L, et al (2019) Pytorch: An imperative style, high-performance deep learning library. In: Advances in neural information processing systems (NIPS), pp 8026–8037
Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) Xnor-net: Imagenet classification using binary convolutional neural networks. In: European conference on computer vision (ECCV), pp 525–542
Romero A, Ballas N, Kahou SE, Chassang A, Gatta C, Bengio Y (2014) Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 4510–4520
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR), pp 1–15
Singh P, Verma VK, Rai P, Namboodiri V (2020) Leveraging filter correlations for deep model compression. In: The IEEE winter conference on applications of computer vision (WACV), pp 835–844
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1–9
Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B (Methodol) 58(1):267–288
Wang X, Zhang B, Li C, Ji R, Han J, Cao X, Liu J (2018) Modulated convolutional networks. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 840–848
Wang Y, Xu C, You S, Tao D, Xu C (2016) Cnnpack: Packing convolutional neural networks in the frequency domain. In: Advances in neural information processing systems (NIPS), pp 253–261
Wen Y, Zhang K, Li Z, Qiao Y (2016) A discriminative feature learning approach for deep face recognition. In: European conference on computer vision (ECCV), pp 499–515
Xu S, Chen H, Liu K, Lii J, Zhang B (2019) Efficient block pruning based on kernel and feature stablization. In: International conference on digital image computing: techniques and applications (DICTA), pp 1–6
Yu R, Li A, Chen CF, Lai JH, Morariu VI, Han X, Gao M, Lin CY, Davis LS (2018) Nisp: Pruning networks using neuron importance score propagation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 9194–9203
Zhang Z, Saligrama V (2015) Rapid: Rapidly accelerated proximal gradient algorithms for convex minimization. In: International conference on acoustics, speech and signal processing (ICASSP), pp 3796–3800
Zoph B, Le QV (2017) Neural architecture search with reinforcement learning. In: International conference on learning representations (ICLR), pp 1–16
Acknowledgements
Baochang Zhang is also with Shenzhen Academy of Aerospace Technology, Shenzhen, China, and he is the corresponding author. He is in part Supported by Shenzhen Science and Technology Program (No.KQTD2016112515134654). The work was supported by the Natural Science Foundation of China (62076016). Baochang Zhang is in part supported by Shenzhen Science and Technology Program (No.KQTD2016112515134654). This study was supported by Grant NO.2019JZZY011101 from the Key Research and Development Program of Shandong Province to Dianmin Sun.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xu, S., Chen, H., Gong, X. et al. Efficient structured pruning based on deep feature stabilization. Neural Comput & Applic 33, 7409–7420 (2021). https://doi.org/10.1007/s00521-021-05828-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-05828-8