{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T05:43:14Z","timestamp":1790833394802,"version":"4.1.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T00:00:00Z","timestamp":1716422400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T00:00:00Z","timestamp":1716422400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2017YFB1401000"],"award-info":[{"award-number":["2017YFB1401000"]}]},{"name":"National Key Research and Development Plan of Shanxi Provence","award":["201903D421007"],"award-info":[{"award-number":["201903D421007"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Intell Syst"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Convolutional neural network (CNN) pruning is a technique used to remove redundant parameters from the network. By doing so, it aims to greatly reduce the computational complexity and scale of the network while still preserving its accuracy. In the CNN, the majority of parameters are weights that form filters. When it comes to pruning, it is more effective to focus on removing redundant filters rather than insignificant weights within filters. The essence of filter pruning lies in determining the significance or contribution of each filter. Filters that have a significant contribution are kept, while others are pruned. Current methods for calculating contribution in pruning often rely on weight magnitude or filter similarity. However, approaches based solely on assume that small weights are unimportant and ignore correlation between filters, which leads to a significant loss of network accuracy. Those based on filter similarity flatten filter tensors into a vector when calculating filter similarity, and lose the important structural information of filters, or the superposition information of the weight convolution in the corresponding space position. These limitations can compromise the accuracy and effectiveness of the pruning process. This paper proposes an adaptive CNN pruning method based on the structural similarity of filters (APSSF) by taking both the structural characteristics of and the correlation between filters into the consideration for pruning filters. APSSF efficiently calculates the distance between the filters by factoring in information from all the dimensions of filters, and clusters the filters according to the distance threshold determined adaptively according to the compression rate, and deletes a certain number of filters from each category. On the CIFAR10 and ImageNet datasets, APSSF outperforms several state-of-the-art methods. On the CIFAR100, APSSF reduces parameters of networks by 91.71% and 74.80% on VGG-16 and ResNet-34, respectively. The accuracy was decreased only by 0.03 on VGG-16, while on ResNet-34, it was increased by 0.04.<\/jats:p>","DOI":"10.1007\/s44196-024-00518-4","type":"journal-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T08:02:52Z","timestamp":1716451372000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["APSSF: Adaptive CNN Pruning Based on Structural Similarity of Filters"],"prefix":"10.1007","volume":"17","author":[{"given":"Lili","family":"Geng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7924-3384","authenticated-orcid":false,"given":"Baoning","family":"Niu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,23]]},"reference":[{"key":"518_CR1","doi-asserted-by":"crossref","unstructured":"Simonyan, K, Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR), pp. 1\u201314 (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"518_CR2","doi-asserted-by":"publisher","unstructured":"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), Las Vegas, NV, USA, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"key":"518_CR3","doi-asserted-by":"publisher","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In:\u00a02017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 1800\u20131807 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.195.","DOI":"10.1109\/CVPR.2017.195"},{"key":"518_CR4","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), vol. 1, no. 2 pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"518_CR5","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., Komodakis, N.: Wide residual networks. arXiv preprint arXiv:1605.07146 (2016)","DOI":"10.5244\/C.30.87"},{"key":"518_CR6","doi-asserted-by":"publisher","unstructured":"Zhang, Q., Shi, Y., Zhang, L., Wang, Y., Tian, Y.: Learning compact networks via similarity-aware channel pruning. In: 2020 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), Shenzhen, China, pp. 145\u2013148. https:\/\/doi.org\/10.1109\/MIPR49039.2020.00037 (2020)","DOI":"10.1109\/MIPR49039.2020.00037"},{"key":"518_CR7","unstructured":"Han, S., Pool, J., Tran, J., Dally, W. L.: Learning both weights and connections for efficient neural networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems, vol. 1, December 2015,\u00a0pp.1135\u20131143 (2015)"},{"key":"518_CR8","doi-asserted-by":"publisher","unstructured":"Carreira-Perpinan, M. A., Idelbayev, Y.: \u201cLearning-Compression\u201d algorithms for neural net pruning. In:\u00a02018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 8532\u20138541. https:\/\/doi.org\/10.1109\/CVPR.2018.00890 (2018)","DOI":"10.1109\/CVPR.2018.00890"},{"issue":"1","key":"518_CR9","doi-asserted-by":"publisher","first-page":"316","DOI":"10.3390\/app13010316","volume":"13","author":"D Ghimire","year":"2023","unstructured":"Ghimire, D., Kim, S.H.: Magnitude and similarity based variable rate filter pruning for efficient convolution neural networks. Appl. Sci. 13(1), 316 (2023). https:\/\/doi.org\/10.3390\/app13010316","journal-title":"Appl. Sci."},{"key":"518_CR10","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H. P.: Pruning filters for efficient convnets. In: Proceedings of International Conference on Learning Representations, pp. 1\u201313 (2017)"},{"key":"518_CR11","doi-asserted-by":"publisher","unstructured":"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 (Long Beach, CA), pp. 4340\u20134349. https:\/\/doi.org\/10.1109\/CVPR.2019.00447 (2019)","DOI":"10.1109\/CVPR.2019.00447"},{"key":"518_CR12","doi-asserted-by":"publisher","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE International Conference on Computer Vision (Venice), pp. 2736\u20132744. https:\/\/doi.org\/10.1109\/ICCV.2017.298 (2017)","DOI":"10.1109\/ICCV.2017.298"},{"key":"518_CR13","doi-asserted-by":"publisher","unstructured":"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), Venice, Italy, pp. 5068\u20135076. https:\/\/doi.org\/10.1109\/ICCV.2017.541 (2017)","DOI":"10.1109\/ICCV.2017.541"},{"key":"518_CR14","unstructured":"Molchanov, P., Tyree, S., Karras, T., Aila, T., Kautz, J.: Pruning convolutional neural networks for resource efficient inference. In: International Conference on Learning Representations (ICLR), pp. 1\u201317 (2017)"},{"key":"518_CR15","doi-asserted-by":"publisher","unstructured":"Molchanov, P., Mallya, A., Tyree, S., Frosio, I., Kautz, J.: Importance estimation for neural network pruning. In:\u00a02019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp. 11256\u201311264. https:\/\/doi.org\/10.1109\/CVPR.2019.01152 (2019)","DOI":"10.1109\/CVPR.2019.01152"},{"key":"518_CR16","doi-asserted-by":"publisher","unstructured":"Yang, T.-J., Chen, Y.-H., Sze, V.: Designing energy-efficient convolutional neural networks using energy-aware pruning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 6071\u20136079. https:\/\/doi.org\/10.1109\/CVPR.2017.643 (2017)","DOI":"10.1109\/CVPR.2017.643"},{"key":"518_CR17","doi-asserted-by":"publisher","unstructured":"Chu, C., Chen, L., Gao, Z.: Similarity based filter pruning for efficient super-resolution models. In: 2020 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), Paris, France, pp. 1\u20137. https:\/\/doi.org\/10.1109\/BMSB49480.2020.9379712 (2020)","DOI":"10.1109\/BMSB49480.2020.9379712"},{"key":"518_CR18","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/s13042-021-01411-8","volume":"13","author":"M Shao","year":"2022","unstructured":"Shao, M., Dai, J., Wang, R., Kuang, J.D., Zuo, W.M.: CSHE: network pruning by using cluster similarity and matrix eigenvalues. Int. J. Mach. Learn. & Cyber. 13, 371\u2013382 (2022). https:\/\/doi.org\/10.1007\/s13042-021-01411-8","journal-title":"Int. J. Mach. Learn. & Cyber."},{"issue":"4","key":"518_CR19","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.1587\/transinf.2017EDL8248","volume":"E101D","author":"LQ Li","year":"2018","unstructured":"Li, L.Q., Xu, Y.H., Zhu, J.: Filter level pruning based on similar feature extraction for convolutional neural networks. IEICE Trans. Inf. Syst. E101D(4), 1203\u20131206 (2018)","journal-title":"IEICE Trans. Inf. Syst."},{"key":"518_CR20","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.knosys.110386","volume":"265","author":"JF Chang","year":"2023","unstructured":"Chang, J.F., Lu, Y., Xue, P., Xu, Y.Q., Wei, Z.: Iterative clustering pruning for convolutional neural networks. Knowl.-Based Syst. 265, 8 (2023). https:\/\/doi.org\/10.1016\/j.knosys.110386","journal-title":"Knowl.-Based Syst."},{"key":"518_CR21","first-page":"201","volume-title":"Deep Learning","author":"G Ian","year":"2024","unstructured":"Ian, G., Yoshua, B., Aaron, C.: Deep Learning, pp. 201\u2013202. The People\u2019s Posts and Telecommunications Press, Beijing (2024)"},{"key":"518_CR22","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical Report, Computer Science Department, University of Toronto, http:\/\/www.cs.toronto.edu\/~kriz\/cifar-10-binary.tar.gz (2009)"},{"key":"518_CR23","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical Report, Computer Science Department, University of Toronto. http:\/\/www.cs.toronto.edu\/~kriz\/cifar-100-binary.tar.gz. (2009)"},{"key":"518_CR24","unstructured":"Jia, D., Wei, D., Socher, R., Li, L. J., Kai, L., Li, F. F.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp. 248\u2013255 (2009)"},{"key":"518_CR25","doi-asserted-by":"publisher","unstructured":"Lin, S.\u00a0et al.: Towards Optimal Structured CNN Pruning via Generative Adversarial Learning. In:\u00a02019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp. 2785\u20132794. https:\/\/doi.org\/10.1109\/CVPR.2019.00290. (2019)","DOI":"10.1109\/CVPR.2019.00290"},{"key":"518_CR26","doi-asserted-by":"publisher","unstructured":"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), Nashville, TN, USA, pp. 14908\u201314917, https:\/\/doi.org\/10.1109\/CVPR46437.2021.01467 (2021)","DOI":"10.1109\/CVPR46437.2021.01467"},{"key":"518_CR27","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/j.neunet.2021.12.017","volume":"147","author":"C Sarvani","year":"2022","unstructured":"Sarvani, C., Ghorai, M., Dubey, S.R., Basha, S.S.: Hrel: filter pruning based on high relevance between activation maps and class labels. Neural Netw. 147, 186\u2013197 (2022)","journal-title":"Neural Netw."},{"key":"518_CR28","doi-asserted-by":"publisher","unstructured":"He, Y., Ding, Y., Liu, P., Zhu, L., Zhang, H., Yang, Y.: Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration. In:\u00a02020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 2006\u20132015. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00208 (2020)","DOI":"10.1109\/CVPR42600.2020.00208"},{"key":"518_CR29","doi-asserted-by":"publisher","unstructured":"Cai, L., An, Z., Yang, C., Xu, Y.: Softer pruning, incremental regularization. In:\u00a02020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy, pp. 224\u2013230, https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412993 (2021)","DOI":"10.1109\/ICPR48806.2021.9412993"}],"container-title":["International Journal of Computational Intelligence Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44196-024-00518-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44196-024-00518-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44196-024-00518-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T20:54:44Z","timestamp":1732049684000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44196-024-00518-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,23]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["518"],"URL":"https:\/\/doi.org\/10.1007\/s44196-024-00518-4","relation":{},"ISSN":["1875-6883"],"issn-type":[{"value":"1875-6883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,23]]},"assertion":[{"value":"25 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflicts of interest relevant to this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"All authors have read and agree to participate in this paper. In addition, the authors confirm that this manuscript has not been submitted to any other journal for simultaneous consideration.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval and Consent to Participate"}},{"value":"All authors appeared in this paper agreed to publication in this journal.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"129"}}