{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:42:27Z","timestamp":1764873747201,"version":"build-2065373602"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2016YFB1200401"],"award-info":[{"award-number":["2016YFB1200401"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1016\/j.jvcir.2020.102867","type":"journal-article","created":{"date-parts":[[2020,8,5]],"date-time":"2020-08-05T21:52:34Z","timestamp":1596664354000},"page":"102867","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":9,"special_numbering":"C","title":["Structured feature sparsity training for convolutional neural network compression"],"prefix":"10.1016","volume":"71","author":[{"given":"Wei","family":"Wang","sequence":"first","affiliation":[]},{"given":"Liqiang","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2020.102867_b0005","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst., Dec."},{"issue":"3","key":"10.1016\/j.jvcir.2020.102867_b0010","doi-asserted-by":"crossref","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":"Int. J. Comput. Vision."},{"key":"10.1016\/j.jvcir.2020.102867_b0015","doi-asserted-by":"crossref","first-page":"102647","DOI":"10.1016\/j.jvcir.2019.102647","article-title":"Image classification towards transmission line fault detection via learning deep quality-aware fine-grained categorization","volume":"64","author":"Wang","year":"2019","journal-title":"J. Vis. Commun. Image Represent"},{"issue":"3","key":"10.1016\/j.jvcir.2020.102867_b0020","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1109\/LGRS.2018.2876378","article-title":"SAR Target Image Classification Based on Transfer Learning and Model Compression","volume":"16","author":"Zhong","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.jvcir.2020.102867_b0025","first-page":"3431","article-title":"Fully Convolutional Networks for Semantic Segmentation","author":"Long","year":"2015","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"10.1016\/j.jvcir.2020.102867_b0030","first-page":"21","article-title":"Coarse-to-fine salient object detection based on deep convolutional neural networks","volume":"64","author":"Li","year":"2018","journal-title":"Signal Processing: Image Communication"},{"key":"10.1016\/j.jvcir.2020.102867_b0035","first-page":"21","article-title":"SSD: single shot multibox detector","author":"Liu","year":"2016","journal-title":"European Conference on Computer Vision (ECCV), Springer"},{"key":"10.1016\/j.jvcir.2020.102867_b0040","doi-asserted-by":"crossref","first-page":"102678","DOI":"10.1016\/j.jvcir.2019.102678","article-title":"Quality-guided key frames selection from video stream based on object detection","volume":"65","author":"Chen","year":"2019","journal-title":"J. Vis. Commun. Image Represent"},{"key":"10.1016\/j.jvcir.2020.102867_b0045","doi-asserted-by":"crossref","unstructured":"Y. Jing, X. Liu, Y. Ding, X. Wang, E. Ding, M. Song, S. Wen, Dynamic Instance Normalization for Arbitrary Style Transfer,in The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020, arXiv preprint arXiv: 1911.06953.","DOI":"10.1609\/aaai.v34i04.5862"},{"year":"2015","series-title":"Very deep convolutional networks for large-scale image recognition, in Proc","author":"Simonyan","key":"10.1016\/j.jvcir.2020.102867_b0050"},{"key":"10.1016\/j.jvcir.2020.102867_b0055","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.jvcir.2020.102867_b0060","doi-asserted-by":"crossref","unstructured":"M. Jaderberg, A. Vedaldi, A. Zisserman, Speeding up convolutional neural networks with low rank expansions. in Proc. BMVC, Sep. 2014.","DOI":"10.5244\/C.28.88"},{"key":"10.1016\/j.jvcir.2020.102867_b0065","first-page":"3123","article-title":"BinaryConnect: training deep neural networks with binary weights during propagations in Adv","author":"Courbariaux","year":"2015","journal-title":"Neural Inf. Process. Syst., Nov."},{"key":"10.1016\/j.jvcir.2020.102867_b0070","first-page":"1","article-title":"Distilling the knowledge in a neural network. in Adv","author":"Hinton","year":"2014","journal-title":"Neural Inf. Process. Syst., Dec."},{"key":"10.1016\/j.jvcir.2020.102867_b0075","article-title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","author":"Howard","year":"2017","journal-title":"[Online]. Available"},{"key":"10.1016\/j.jvcir.2020.102867_b0080","first-page":"598","article-title":"Optimal brain damage, in Adv","author":"LeCun","year":"1989","journal-title":"Neural Inf. Process. Syst., Nov."},{"key":"10.1016\/j.jvcir.2020.102867_b0085","unstructured":"H. Li, A. Kadav, I. Durdanovic, H. Samet, and H.P. Graf. Pruning filters for efficient convnets. in Proc. Int. Conf. Learn. Represent., Toulon, France, Apr. 2017."},{"key":"10.1016\/j.jvcir.2020.102867_b0090","series-title":"IEEE international conference on neural networks","first-page":"293","article-title":"Optimal brain surgeon and general network pruning","author":"Hassibi","year":"1993"},{"key":"10.1016\/j.jvcir.2020.102867_b0095","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network, in Adv","author":"Han","year":"2015","journal-title":"Neural Inf. Process. Syst., Dec."},{"key":"10.1016\/j.jvcir.2020.102867_b0100","doi-asserted-by":"crossref","unstructured":"S. Han, X. Liu, H. Mao, J. Pu, A. Pedram, M. A. Horowitz, and W. J. Dally, Eie: Efficient Inference Engine on Compressed Deep Neural Network, in 2016 ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), Aug. 2016, pp. 243\u2013254.","DOI":"10.1109\/ISCA.2016.30"},{"key":"10.1016\/j.jvcir.2020.102867_b0105","first-page":"2074","article-title":"Learning Structured Sparsity in Deep Neural Networks, in Adv","author":"Wen","year":"2016","journal-title":"Neural Inf. Process. Syst., Dec."},{"issue":"10","key":"10.1016\/j.jvcir.2020.102867_b0110","doi-asserted-by":"crossref","first-page":"2525","DOI":"10.1109\/TPAMI.2018.2858232","article-title":"ThiNet: pruning CNN filters for a thinner net","volume":"41","author":"Luo","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2020.102867_b0115","doi-asserted-by":"crossref","first-page":"102582","DOI":"10.1016\/j.jvcir.2019.102582","article-title":"Reliable identification of redundant kernels for convolutional neural network compression","volume":"63","author":"Wang","year":"2019","journal-title":"J. Vis. Commun. Image Represent"},{"key":"10.1016\/j.jvcir.2020.102867_b0120","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, Oct. 2017, pp. 2755\u20132763.","DOI":"10.1109\/ICCV.2017.298"},{"key":"10.1016\/j.jvcir.2020.102867_b0125","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","author":"Denton","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2020.102867_b0130","first-page":"67","article-title":"On Compressing Deep Models by Low Rank and Sparse Decomposition","author":"Yu","year":"2017","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"10.1016\/j.jvcir.2020.102867_b0135","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"658","article-title":"Coordinating filters for faster deep neural networks","author":"Wen","year":"2017"},{"key":"10.1016\/j.jvcir.2020.102867_b0140","article-title":"Speeding-up convolutional neural networks using fine-tuned cp-decomposition","author":"Lebedev","year":"2014","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"10.1016\/j.jvcir.2020.102867_b0145","unstructured":"C. Tai, T. Xiao, Y. Zhang, X. Wang, W. E, Convolutional neural networks with low-rank regularization, 2015. arXiv preprint arXiv:1511.06067."},{"key":"10.1016\/j.jvcir.2020.102867_b0150","article-title":"Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding, in","author":"Han","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"10.1016\/j.jvcir.2020.102867_b0155","unstructured":"S. Gupta, A. Agrawal,K. Gopalakrishnan,P. Narayanan, deep learning with limited numerical precision. arXiv preprint arXiv: 1502.02551, 2015."},{"key":"10.1016\/j.jvcir.2020.102867_b0160","doi-asserted-by":"crossref","unstructured":"S. Hashemi,N. Anthony,H. Tann,R. I. Bahar,S. Reda. Understanding the impact of precision quantization on the accuracy and energy of neural networks. arXiv preprint arXiv: 1612.03940v1, 2016.","DOI":"10.23919\/DATE.2017.7927224"},{"key":"10.1016\/j.jvcir.2020.102867_b0165","unstructured":"M. Courbariaux,I. Hubara,D. Soudry,R. El-Yaniv,Y. Bengio, Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1. arXiv preprint arXiv: 1602.02830, 2016."},{"key":"10.1016\/j.jvcir.2020.102867_b0170","unstructured":"Y. Gong, L. Liu, M. Yang, L. Bourdev, Compressing deep convolutional networksusing vector quantization, 2014. arXiv preprint arXiv:1412.6115."},{"key":"10.1016\/j.jvcir.2020.102867_b0175","unstructured":"J. Ba and R. Caruana, Do deep nets really need to be deep? in Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, Dec. 2014, pp. 2654\u20132662."},{"key":"10.1016\/j.jvcir.2020.102867_b0180","article-title":"Amalgamating Knowledge towards Comprehensive Classification","author":"Shen","year":"2019","journal-title":"AAAI Conference"},{"key":"10.1016\/j.jvcir.2020.102867_b0185","first-page":"2824","article-title":"Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing","author":"Ye","year":"2019","journal-title":"Depth Estimation, and More, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"10.1016\/j.jvcir.2020.102867_b0190","doi-asserted-by":"crossref","unstructured":"X. Zhang, X. Zhou, M. Lin, J. Sun, Shufflenet: An extremely efficient convolutional neural network for mobile devices. arXiv preprint arXiv:1707.01083, 2017.","DOI":"10.1109\/CVPR.2018.00716"},{"key":"10.1016\/j.jvcir.2020.102867_b0195","doi-asserted-by":"crossref","unstructured":"M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L.C. Chen, Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation. arXiv preprint arXiv:1801.04381, 2018.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10.1016\/j.jvcir.2020.102867_b0200","article-title":"Xception Deep Learning with Depthwise Separable Convolutions","author":"Chollet","year":"2016","journal-title":"arXiv preprint arXiv:1610.02357"},{"key":"10.1016\/j.jvcir.2020.102867_b0205","doi-asserted-by":"crossref","unstructured":"N. Ma, X. Zhang, H.T. Zheng, J. Sun, ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design. arXiv preprint arXiv:1807.11164v1, 2018.","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"10.1016\/j.jvcir.2020.102867_b0210","series-title":"5th International Conference on Learning Representations","article-title":"Neural Architecture Search with Reinforcement Learning","author":"Zoph","year":"2017"},{"key":"10.1016\/j.jvcir.2020.102867_b0215","series-title":"5th International Conference on Learning Representations","article-title":"Designing Neural Network Architectures using Reinforcement Learning","author":"Baker","year":"2017"},{"key":"10.1016\/j.jvcir.2020.102867_b0220","series-title":"Proceedings of the 34thInternational Conference on Machine Learning","first-page":"2902","article-title":"Large-scale evolution of image classifiers","author":"Real","year":"2017"},{"key":"10.1016\/j.jvcir.2020.102867_b0225","unstructured":"B. Hassibi and D. G. Stork. Second order derivatives for network pruning: Optimal brain surgeon. In: Advances in neural information processing systems. 1993, pp. 164\u2013171."},{"key":"10.1016\/j.jvcir.2020.102867_b0230","first-page":"2554","article-title":"Fast convnets using group-wise brain damage, in","author":"Lebedev","year":"2016","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"10.1016\/j.jvcir.2020.102867_b0235","article-title":"Network Trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016","journal-title":"[Online]. Available"},{"key":"10.1016\/j.jvcir.2020.102867_b0240","article-title":"Learning multiple layers of features from tiny images, in","author":"Krizhevsky","year":"2009","journal-title":"Tech Report"},{"key":"10.1016\/j.jvcir.2020.102867_b0245","unstructured":"Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, A. Y. Ng, Reading digits in natural images with unsupervised feature learning, in: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2011."},{"key":"10.1016\/j.jvcir.2020.102867_b0250","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1117\/12.242059","article-title":"MSTAR extended operating conditions: A tutorial","volume":"2757","author":"Keydel","year":"1996","journal-title":"Proc. SPIE"},{"issue":"4","key":"10.1016\/j.jvcir.2020.102867_b0255","doi-asserted-by":"crossref","first-page":"2196","DOI":"10.1109\/TGRS.2017.2776357","article-title":"SAR automatic target recognition based on multiview deep learning framework","volume":"56","author":"Pei","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"9","key":"10.1016\/j.jvcir.2020.102867_b0260","doi-asserted-by":"crossref","first-page":"1484","DOI":"10.1109\/LGRS.2017.2717486","article-title":"Improving SAR automatic target recognition models with transfer learning from simulated data","volume":"14","author":"Malmgren-Hansen","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320320301176?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320320301176?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T02:45:06Z","timestamp":1760928306000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320320301176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":52,"alternative-id":["S1047320320301176"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2020.102867","relation":{},"ISSN":["1047-3203"],"issn-type":[{"type":"print","value":"1047-3203"}],"subject":[],"published":{"date-parts":[[2020,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Structured feature sparsity training for convolutional neural network compression","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2020.102867","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2020 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"102867"}}