{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T08:22:24Z","timestamp":1742804544469,"version":"3.37.3"},"reference-count":54,"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\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971290"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1016\/j.neucom.2020.01.113","type":"journal-article","created":{"date-parts":[[2020,3,9]],"date-time":"2020-03-09T06:00:33Z","timestamp":1583733633000},"page":"216-226","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["L<\/mml:mi>1<\/mml:mn><\/mml:msub><\/mml:math>-norm low-rank linear approximation for accelerating deep neural networks"],"prefix":"10.1016","volume":"400","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5000-100X","authenticated-orcid":false,"given":"Zhiqun","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Hengyou","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Zhihai","family":"He","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.neucom.2020.01.113_bib0001","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1007\/978-3-642-61159-9_32","article-title":"A l1-norm PCA and a heuristic approach","volume":"1","author":"Baccini","year":"1996","journal-title":"Ordinal Symbol. Data Anal."},{"issue":"1","key":"10.1016\/j.neucom.2020.01.113_bib0002","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1137\/080716542","article-title":"A fast iterative shrinkage-thresholding algorithm for linear inverse problems","volume":"2","author":"Beck","year":"2009","journal-title":"SIAM J. Imaging Sci."},{"year":"2014","series-title":"Constrained Optimization and Lagrange Multiplier Methods","author":"Bertsekas","key":"10.1016\/j.neucom.2020.01.113_bib0003"},{"issue":"3","key":"10.1016\/j.neucom.2020.01.113_bib0004","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1145\/1970392.1970395","article-title":"Robust principal component analysis?","volume":"58","author":"Cand\u00e8s","year":"2011","journal-title":"J. ACM (JACM)"},{"key":"10.1016\/j.neucom.2020.01.113_bib0005","series-title":"Advances in Neural Information Processing Systems","first-page":"3123","article-title":"Binaryconnect: training deep neural networks with binary weights during propagations","author":"Courbariaux","year":"2015"},{"key":"10.1016\/j.neucom.2020.01.113_bib0006","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:1602.02830(2016)."},{"key":"10.1016\/j.neucom.2020.01.113_bib0007","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.neucom.2020.01.113_bib0008","series-title":"Advances in Neural Information Processing Systems","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","author":"Denton","year":"2014"},{"issue":"1\u20133","key":"10.1016\/j.neucom.2020.01.113_bib0009","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/BF01581204","article-title":"On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators","volume":"55","author":"Eckstein","year":"1992","journal-title":"Math. Program."},{"key":"10.1016\/j.neucom.2020.01.113_bib0010","series-title":"Advances in Neural Information Processing Systems","first-page":"947","article-title":"Perforatedcnns: acceleration through elimination of redundant convolutions","author":"Figurnov","year":"2016"},{"key":"10.1016\/j.neucom.2020.01.113_bib0011","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"key":"10.1016\/j.neucom.2020.01.113_bib0012","series-title":"Procrustes Problems","volume":"30","author":"Gower","year":"2004"},{"issue":"99","key":"10.1016\/j.neucom.2020.01.113_sbref0012","article-title":"Low-rank matrix recovery via robust outlier estimation","volume":"PP","author":"Guo","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.neucom.2020.01.113_bib0014","unstructured":"S. Han, H. Mao, W.J. Dally, Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding, arXiv:1510.00149(2015a)."},{"key":"10.1016\/j.neucom.2020.01.113_bib0015","series-title":"Advances in Neural Information Processing Systems","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"Han","year":"2015"},{"key":"10.1016\/j.neucom.2020.01.113_bib0016","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2961","article-title":"Mask R-CNN","author":"He","year":"2017"},{"key":"10.1016\/j.neucom.2020.01.113_bib0017","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2020.01.113_bib0018","series-title":"Complex-valued neural networks: theories and applications","volume":"5","author":"Hirose","year":"2003"},{"key":"10.1016\/j.neucom.2020.01.113_bib0019","unstructured":"A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam, Mobilenets: efficient convolutional neural networks for mobile vision applications, arXiv:1704.04861(2017)."},{"issue":"1","key":"10.1016\/j.neucom.2020.01.113_bib0020","first-page":"6869","article-title":"Quantized neural networks: training neural networks with low precision weights and activations","volume":"18","author":"Hubara","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.neucom.2020.01.113_bib0021","unstructured":"F.N. Iandola, S. Han, M.W. Moskewicz, K. Ashraf, W.J. Dally, K. Keutzer, Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size, arXiv:1602.07360(2016)."},{"key":"10.1016\/j.neucom.2020.01.113_bib0022","series-title":"Proceedings of the British Machine Vision Conference. BMVA Press","article-title":"Speeding up convolutional neural networks with low rank expansions","author":"Jaderberg","year":"2014"},{"key":"10.1016\/j.neucom.2020.01.113_bib0023","series-title":"International Encyclopedia of Statistical Science","first-page":"1094","article-title":"Principal Component Analysis","author":"Jolliffe","year":"2011"},{"year":"2003","series-title":"Robust Subspace Computation Using L1 Norm","author":"Ke","key":"10.1016\/j.neucom.2020.01.113_bib0024"},{"key":"10.1016\/j.neucom.2020.01.113_bib0025","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905)","first-page":"739","article-title":"Robust l1 norm factorization in the presence of outliers and missing data by alternative convex programming","volume":"1","author":"Ke","year":"2005"},{"key":"10.1016\/j.neucom.2020.01.113_bib0026","series-title":"Technical Report","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.neucom.2020.01.113_bib0027","series-title":"Advances in Neural Information Processing systems","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"10.1016\/j.neucom.2020.01.113_bib0028","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2554","article-title":"Fast convnets using group-wise brain damage","author":"Lebedev","year":"2016"},{"issue":"11","key":"10.1016\/j.neucom.2020.01.113_bib0029","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.neucom.2020.01.113_bib0030","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2790","article-title":"Towards optimal structured CNN pruning via generative adversarial learning","author":"Lin","year":"2019"},{"key":"10.1016\/j.neucom.2020.01.113_bib0031","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.neucom.2020.01.113_bib0032","series-title":"Proceedings of the IEEE Conference on Computer Vision and pattern Recognition","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation","author":"Long","year":"2015"},{"key":"10.1016\/j.neucom.2020.01.113_bib0033","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"5058","article-title":"Thinet: a filter level pruning method for deep neural network compression","author":"Luo","year":"2017"},{"key":"10.1016\/j.neucom.2020.01.113_bib0034","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"116","article-title":"Shufflenet v2: Practical guidelines for efficient CNN architecture design","author":"Ma","year":"2018"},{"key":"10.1016\/j.neucom.2020.01.113_bib0035","series-title":"Proceedings of the 2000 IEEE Signal Processing Society Workshop Neural Networks for Signal Processing X","first-page":"289","article-title":"Robust principal component analysis","volume":"1","author":"Partridge","year":"2000"},{"key":"10.1016\/j.neucom.2020.01.113_bib0036","unstructured":"A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga, A. Lerer, Automatic differentiation in pytorch(2017)."},{"key":"10.1016\/j.neucom.2020.01.113_bib0037","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"525","article-title":"Xnor-net: Imagenet classification using binary convolutional neural networks","author":"Rastegari","year":"2016"},{"issue":"9","key":"10.1016\/j.neucom.2020.01.113_bib0038","doi-asserted-by":"crossref","first-page":"e0138028","DOI":"10.1371\/journal.pone.0138028","article-title":"Robust generalized low rank approximations of matrices","volume":"10","author":"Shi","year":"2015","journal-title":"PLoS ONE"},{"key":"10.1016\/j.neucom.2020.01.113_bib0039","unstructured":"K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556(2014)."},{"issue":"5","key":"10.1016\/j.neucom.2020.01.113_bib0040","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/s002000100081","article-title":"Constrained principal component analysis: a comprehensive theory","volume":"12","author":"Takane","year":"2001","journal-title":"Appl. Algebra Eng. Commun. Comput."},{"issue":"1","key":"10.1016\/j.neucom.2020.01.113_bib0041","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1016\/j.csda.2007.02.014","article-title":"Regularized linear and kernel redundancy analysis","volume":"52","author":"Takane","year":"2007","journal-title":"Comput. Stat. Data Anal."},{"issue":"4","key":"10.1016\/j.neucom.2020.01.113_bib0042","doi-asserted-by":"crossref","first-page":"1777","DOI":"10.1109\/TIP.2017.2781425","article-title":"Reweighted low-rank matrix analysis with structural smoothness for image denoising","volume":"27","author":"Wang","year":"2017","journal-title":"IEEE Trans. Image Process."},{"issue":"5","key":"10.1016\/j.neucom.2020.01.113_bib0043","doi-asserted-by":"crossref","first-page":"969","DOI":"10.1109\/TMM.2016.2638624","article-title":"Robust generalized low-rank decomposition of multimatrices for image recovery","volume":"19","author":"Wang","year":"2016","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.neucom.2020.01.113_bib0044","series-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","first-page":"1","article-title":"Augem: automatically generate high performance dense linear algebra kernels on x86 cpus","author":"Wang","year":"2013"},{"key":"10.1016\/j.neucom.2020.01.113_bib0045","first-page":"537","article-title":"A new gradient projection method for matrix completion","volume":"258","author":"Wen","year":"2015","journal-title":"Appl. Math. Comput."},{"key":"10.1016\/j.neucom.2020.01.113_bib0046","series-title":"Advances in Neural Information Processing Systems","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"Wen","year":"2016"},{"key":"10.1016\/j.neucom.2020.01.113_bib0047","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.neucom.2020.01.113_bib0048","series-title":"Advances in Neural Information Processing Systems","first-page":"2080","article-title":"Robust principal component analysis: Exact recovery of corrupted low-rank matrices via convex optimization","author":"Wright","year":"2009"},{"key":"10.1016\/j.neucom.2020.01.113_bib0049","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"9194","article-title":"NISP: Pruning networks using neuron importance score propagation","author":"Yu","year":"2018"},{"key":"10.1016\/j.neucom.2020.01.113_bib0050","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6848","article-title":"Shufflenet: an extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2018"},{"issue":"10","key":"10.1016\/j.neucom.2020.01.113_bib0051","doi-asserted-by":"crossref","first-page":"1943","DOI":"10.1109\/TPAMI.2015.2502579","article-title":"Accelerating very deep convolutional networks for classification and detection","volume":"38","author":"Zhang","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2020.01.113_bib0052","series-title":"Proceedings of the IPAM Workshop on Continuous Optimization","article-title":"Recent advances in alternating direction methods: Practice and theory","author":"Zhang","year":"2010"},{"issue":"1","key":"10.1016\/j.neucom.2020.01.113_bib0053","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1186\/s13662-018-1716-6","article-title":"Periodic solutions for complex-valued neural networks of neutral type by combining graph theory with coincidence degree theory","volume":"2018","author":"Zhang","year":"2018","journal-title":"Adv. Differ. Equ."},{"key":"10.1016\/j.neucom.2020.01.113_bib0054","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2780","article-title":"Variational convolutional neural network pruning","author":"Zhao","year":"2019"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231220303027?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231220303027?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,5,22]],"date-time":"2020-05-22T12:58:34Z","timestamp":1590152314000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231220303027"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":54,"alternative-id":["S0925231220303027"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2020.01.113","relation":{},"ISSN":["0925-2312"],"issn-type":[{"type":"print","value":"0925-2312"}],"subject":[],"published":{"date-parts":[[2020,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"-norm low-rank linear approximation for accelerating deep neural networks","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2020.01.113","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2020 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}