{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T21:29:59Z","timestamp":1774128599537,"version":"3.50.1"},"reference-count":38,"publisher":"SAGE Publications","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2023,7,20]]},"abstract":"<jats:p>With the help of network compression algorithms, deep neural networks can be applied on low-power embedded systems and mobile devices such as drones, satellites, and smartphones. Filter pruning is a sub-direction of network compression research, which reduces memory and computational consumption by reducing the number of parameters of model filters. Previous works utilized the \u201cmore-simple-less-important\u201d criterion for pruning filters. That is, filters with the smaller norm or more sparse weights in the network are preferentially pruned. In this paper, we found that feature maps are not fully positively correlated with the sparsity of filter weights by observing the visualization of feature maps and the corresponding filters. Hence, we came up with the idea that the priority of filter pruning should be determined by redundancy rather than sparsity. The redundancy of a filter is the measure of whether the output of the filter is repeated with other filters. Based on this, we defined a criterion called redundancy index to rank the filters and introduced it into our filter pruning strategy. Extensive experiments demonstrate the effectiveness of our approach on different model architectures, including VGGNet, GoogleNet, DenseNet, and ResNet. The models compressed with our strategy surpass the state-of-the-art in terms of Floating Point Operations Per Second (FLOPs), parameters reduction, and classification accuracy.<\/jats:p>","DOI":"10.3233\/ida-226810","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T17:06:46Z","timestamp":1685725606000},"page":"911-933","source":"Crossref","is-referenced-by-count":3,"title":["Filter pruning via feature map clustering"],"prefix":"10.1177","volume":"27","author":[{"given":"Wei","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"}]},{"given":"Yongxing","family":"He","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"}]},{"given":"Xiaoyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"}]},{"given":"Yongchuan","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"},{"name":"Alibaba-Zhejiang University Joint Research Institute of Frontier Technologise, Hangzhou, Zhejiang, China"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-226810_ref4","doi-asserted-by":"crossref","unstructured":"F. Han, L. Yu and Y. Jiang, Computer-aided diagnosis system of lung carcinoma using Convolutional Neural Networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp.\u00a0690\u2013691.","DOI":"10.1109\/CVPRW50498.2020.00353"},{"key":"10.3233\/IDA-226810_ref5","doi-asserted-by":"crossref","unstructured":"C. Chen, A. Seff, A. Kornhauser and J. Xiao, Deepdriving: Learning affordance for direct perception in autonomous driving, in: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp.\u00a02722\u20132730.","DOI":"10.1109\/ICCV.2015.312"},{"key":"10.3233\/IDA-226810_ref6","doi-asserted-by":"crossref","unstructured":"D. Ye, Z. Liu, M. Sun, B. Shi, P. Zhao, H. Wu, H. Yu, S. Yang, X. Wu, Q. Guo et al., Mastering complex control in moba games with deep reinforcement learning, in: Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI), Vol.\u00a034, 2020, pp.\u00a06672\u20136679.","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"10.3233\/IDA-226810_ref7","unstructured":"W. Chen, J. Wilson, S. Tyree, K. Weinberger and Y. Chen, Compressing neural networks with the hashing trick, in: Proceedings of the International Conference on Machine Learning (ICML), PMLR, 2015, pp.\u00a02285\u20132294."},{"key":"10.3233\/IDA-226810_ref8","unstructured":"H. Li, A. Kadav, I. Durdanovic, H. Samet and H.P. Graf, Pruning filters for efficient convnets, in: Proceedings of the International Conference on Learning Representations (ICLR), 2017."},{"key":"10.3233\/IDA-226810_ref9","doi-asserted-by":"crossref","unstructured":"H. Li, C. Yan, S. Lin, X. Zheng, B. Zhang, F. Yang and R. Ji, Pams: Quantized super-resolution via parameterized max scale, in: Proceedings of the European Conference on Computer Vision (ECCV), Springer, 2020, pp.\u00a0564\u2013580.","DOI":"10.1007\/978-3-030-58595-2_34"},{"issue":"12","key":"10.3233\/IDA-226810_ref10","doi-asserted-by":"crossref","first-page":"2889","DOI":"10.1109\/TPAMI.2018.2873305","article-title":"Holistic cnn compression via low-rank decomposition with knowledge transfer","volume":"41","author":"Lin","year":"2018","journal-title":"TPAMI"},{"key":"10.3233\/IDA-226810_ref11","doi-asserted-by":"crossref","unstructured":"T. Li, J. Li, Z. Liu and C. Zhang, Few sample knowledge distillation for efficient network compression, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp.\u00a014639\u201314647.","DOI":"10.1109\/CVPR42600.2020.01465"},{"key":"10.3233\/IDA-226810_ref12","doi-asserted-by":"crossref","unstructured":"X. Zheng, R. Ji, L. Tang, B. Zhang, J. Liu and Q. Tian, Multinomial distribution learning for effective neural architecture search, in: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019, pp.\u00a01304\u20131313.","DOI":"10.1109\/ICCV.2019.00139"},{"key":"10.3233\/IDA-226810_ref13","doi-asserted-by":"crossref","unstructured":"J.-H. Luo, J. Wu and W. Lin, Thinet: A filter level pruning method for deep neural network compression, in: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp.\u00a05058\u20135066.","DOI":"10.1109\/ICCV.2017.541"},{"key":"10.3233\/IDA-226810_ref15","doi-asserted-by":"crossref","unstructured":"Y. He, P. Liu, Z. Wang, Z. Hu and Y. Yang, Filter pruning via geometric median for deep convolutional neural networks acceleration, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp.\u00a04340\u20134349.","DOI":"10.1109\/CVPR.2019.00447"},{"key":"10.3233\/IDA-226810_ref16","doi-asserted-by":"crossref","unstructured":"S. Lin, R. Ji, Y. Li, Y. Wu, F. Huang and B. Zhang, Accelerating Convolutional Networks via Global & Dynamic Filter Pruning, in: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), Vol.\u00a02, 2018, p.\u00a08.","DOI":"10.24963\/ijcai.2018\/336"},{"key":"10.3233\/IDA-226810_ref17","doi-asserted-by":"crossref","unstructured":"M. Lin, R. Ji, Y. Wang, Y. Zhang, B. Zhang, Y. Tian and L. Shao, Hrank: Filter pruning using high-rank feature map, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp.\u00a01529\u20131538.","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"10.3233\/IDA-226810_ref20","doi-asserted-by":"crossref","unstructured":"Y. He, X. Zhang and J. Sun, Channel pruning for accelerating very deep neural networks, in: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp.\u00a01389\u20131397.","DOI":"10.1109\/ICCV.2017.155"},{"key":"10.3233\/IDA-226810_ref21","unstructured":"S. Hanson and L. Pratt, Comparing biases for minimal network construction with back-propagation, in: Proceedings of the Neural Information Processing Systems (NeurIPS), 1988."},{"key":"10.3233\/IDA-226810_ref22","unstructured":"Y. LeCun, J. Denker and S. Solla, Optimal brain damage, in: Proceedings of the Neural Information Processing Systems (NeurIPS), 1989."},{"key":"10.3233\/IDA-226810_ref23","unstructured":"S. Han, J. Pool, J. Tran and W. Dally, Learning both weights and connections for efficient neural network, in: Proceedings of the Neural Information Processing Systems (NeurIPS), 2015."},{"key":"10.3233\/IDA-226810_ref24","unstructured":"Y. Guo, A. Yao and Y. Chen, Dynamic network surgery for efficient dnns, in: Proceedings of the Neural Information Processing Systems (NeurIPS), 2016."},{"key":"10.3233\/IDA-226810_ref25","doi-asserted-by":"crossref","unstructured":"T. Zhang, S. Ye, K. Zhang, J. Tang, W. Wen, M. Fardad and Y. Wang, A systematic dnn weight pruning framework using alternating direction method of multipliers, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp.\u00a0184\u2013199.","DOI":"10.1007\/978-3-030-01237-3_12"},{"key":"10.3233\/IDA-226810_ref27","doi-asserted-by":"crossref","unstructured":"Z. Liu, J. Li, Z. Shen, G. Huang, S. Yan and C. Zhang, Learning efficient convolutional networks through network slimming, in: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp.\u00a02736\u20132744.","DOI":"10.1109\/ICCV.2017.298"},{"issue":"2","key":"10.3233\/IDA-226810_ref30","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in PCM","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Transactions on Information Theory"},{"key":"10.3233\/IDA-226810_ref31","unstructured":"L. Van\u00a0der Maaten and G. Hinton, Visualizing data using t-SNE, Journal of Machine Learning Research 9(11) (2008)."},{"key":"10.3233\/IDA-226810_ref32","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: A graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"Journal of Computational and Applied Mathematics"},{"key":"10.3233\/IDA-226810_ref33","doi-asserted-by":"crossref","unstructured":"C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A. Rabinovich, Going deeper with convolutions, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp.\u00a01\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"3","key":"10.3233\/IDA-226810_ref34","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"10.3233\/IDA-226810_ref35","doi-asserted-by":"crossref","unstructured":"G. Huang, Z. Liu, L. Van Der\u00a0Maaten and K.Q. Weinberger, Densely connected convolutional networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp.\u00a04700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"10.3233\/IDA-226810_ref36","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren and J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp.\u00a0770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.3233\/IDA-226810_ref37","unstructured":"A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga and A. Lerer, Automatic Differentiation in PyTorch, in: NIPS Autodiff Workshop, 2017."},{"key":"10.3233\/IDA-226810_ref38","unstructured":"D. Kingma and J. Ba, Adam: A method for stochastic optimization, in: International Conference on Learning Representations (ICLR), 2014."},{"key":"10.3233\/IDA-226810_ref39","unstructured":"Y. Sui, M. Yin, Y. Xie, H. Phan, S. Aliari\u00a0Zonouz and B. Yuan, CHIP: CHannel Independence-based Pruning for Compact Neural Networks, in: Proceedings of the Neural Information Processing Systems (NeurIPS), 2021."},{"key":"10.3233\/IDA-226810_ref40","doi-asserted-by":"crossref","unstructured":"C. Zhao, B. Ni, J. Zhang, Q. Zhao, W. Zhang and Q. Tian, Variational convolutional neural network pruning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp.\u00a02780\u20132789.","DOI":"10.1109\/CVPR.2019.00289"},{"key":"10.3233\/IDA-226810_ref41","doi-asserted-by":"crossref","unstructured":"Z. Huang and N. Wang, Data-driven sparse structure selection for deep neural networks, in: Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp.\u00a0304\u2013320.","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"10.3233\/IDA-226810_ref42","doi-asserted-by":"crossref","unstructured":"S. Lin, R. Ji, C. Yan, B. Zhang, L. Cao, Q. Ye, F. Huang and D. Doermann, Towards optimal structured cnn pruning via generative adversarial learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp.\u00a02790\u20132799.","DOI":"10.1109\/CVPR.2019.00290"},{"issue":"1","key":"10.3233\/IDA-226810_ref43","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1049\/ipr2.12338","article-title":"Learning compact ConvNets through filter pruning based on the saliency of a feature map","volume":"16","author":"Liu","year":"2022","journal-title":"IET Image Processing"},{"key":"10.3233\/IDA-226810_ref44","unstructured":"Y. Tang, Y. Wang, Y. Xu, D. Tao, C. XU, C. Xu and C. Xu, SCOP: Scientific Control for Reliable Neural Network Pruning, in: Proceedings of the Neural Information Processing Systems (NeurIPS), 2020, pp.\u00a010936\u201310947."},{"key":"10.3233\/IDA-226810_ref45","doi-asserted-by":"crossref","first-page":"107860","DOI":"10.1016\/j.asoc.2021.107860","article-title":"RFPruning: A retraining-free pruning method for accelerating convolutional neural networks","volume":"113","author":"Wang","year":"2021","journal-title":"Applied Soft Computing"},{"key":"10.3233\/IDA-226810_ref46","doi-asserted-by":"crossref","unstructured":"S. Gao, F. Huang, W. Cai and H. Huang, Network Pruning via Performance Maximization, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp.\u00a09270\u20139280.","DOI":"10.1109\/CVPR46437.2021.00915"},{"key":"10.3233\/IDA-226810_ref48","doi-asserted-by":"crossref","unstructured":"R. Yu, A. Li, C.-F. Chen, J.-H. Lai, V.I. Morariu, X. Han, M. Gao, C.-Y. Lin and L.S. Davis, Nisp: Pruning networks using neuron importance score propagation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp.\u00a09194\u20139203.","DOI":"10.1109\/CVPR.2018.00958"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-226810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T07:51:57Z","timestamp":1741679517000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-226810"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,20]]},"references-count":38,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.3233\/ida-226810","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,20]]}}}