{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T10:43:27Z","timestamp":1755600207179,"version":"3.37.3"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772124"],"award-info":[{"award-number":["61772124"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009016","name":"Northeastern University at Qinhuangdao","doi-asserted-by":"publisher","award":["XNK2015003"],"award-info":[{"award-number":["XNK2015003"]}],"id":[{"id":"10.13039\/501100009016","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2960315","type":"journal-article","created":{"date-parts":[[2019,12,17]],"date-time":"2019-12-17T21:02:17Z","timestamp":1576616537000},"page":"183604-183613","source":"Crossref","is-referenced-by-count":9,"title":["S-DenseNet: A DenseNet Compression Model Based on Convolution Grouping Strategy Using Skyline Method"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2803-4291","authenticated-orcid":false,"given":"Changyong","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3509-664X","authenticated-orcid":false,"given":"Xin","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9644-0435","authenticated-orcid":false,"given":"Haitao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4572-059X","authenticated-orcid":false,"given":"Xin","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1326-6559","authenticated-orcid":false,"given":"Jiarui","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1080-0859","authenticated-orcid":false,"given":"Yuhai","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NIPS"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref38"},{"key":"ref33","first-page":"122","article-title":"ShuffleNet V2: Practical guidelines for efficient CNN architecture design","author":"ma","year":"2018","journal-title":"Proc ECCV"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref31","article-title":"A closer look at network resolution for efficient network design","author":"yang","year":"2019","journal-title":"arXiv 1909 12978"},{"key":"ref30","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00291"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.117"},{"key":"ref34","article-title":"SqueezeNet: AlexNet-level accuracy with 50\n$\\times$\n fewer parameters and <0.5MB model size","author":"iandola","year":"2016","journal-title":"arXiv 1602 07360"},{"key":"ref28","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref27","article-title":"On the efficacy of knowledge distillation","author":"cho","year":"2019","journal-title":"arXiv 1910 01348"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2875586"},{"key":"ref1","first-page":"581","article-title":"ColorNet: Investigating the importance of color spaces for image classification","author":"gowda","year":"2019","journal-title":"Proc ACCV"},{"key":"ref20","first-page":"192","article-title":"Sparsely aggregated convolutional networks","author":"zhu","year":"2018","journal-title":"Proc ECCV"},{"key":"ref22","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"hu","year":"2016","journal-title":"arXiv 1607 03250"},{"key":"ref21","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015","journal-title":"Proc ICLR"},{"key":"ref24","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref23","first-page":"2800","article-title":"Exploiting Kernel sparsity and entropy for interpretable CNN compression","author":"li","year":"2019","journal-title":"Proc CVPR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013771"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref50","first-page":"1","article-title":"Fractalnet: Ultra-deep neural networks without residuals","author":"larsson","year":"2016","journal-title":"Proc ICLR"},{"key":"ref51","article-title":"Pruning from scratch","author":"wang","year":"2019","journal-title":"arXiv 1909 12579"},{"key":"ref52","article-title":"Associative convolutional layers","author":"omidvar","year":"2019","journal-title":"arXiv 1906 04309"},{"key":"ref10","article-title":"Log-DenseNet: How to sparsify a densenet","author":"hu","year":"2017","journal-title":"arXiv 1711 00002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-019-01433-4"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/140958529"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.410"},{"key":"ref14","article-title":"ShiftCNN: Generalized low-precision architecture for inference of convolutional neural networks","author":"gudovskiy","year":"2017","journal-title":"arXiv 1706 02393"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"ref16","article-title":"Improving the speed of neural networks on CPUs","author":"vanhoucke","year":"2011","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref17","first-page":"1737","article-title":"Deep learning with limited numerical precision","author":"suyog","year":"2015","journal-title":"Proceedings of ICL"},{"key":"ref18","first-page":"4923","article-title":"Binary ensemble neural network: More bits per network or more networks per bit?","author":"zhu","year":"2019","journal-title":"Proc CVPR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref6","first-page":"4278","article-title":"Inception-v4, inception-ResNet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc AAAI"},{"key":"ref5","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"Proc ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc ECCV"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2777994"},{"key":"ref46","first-page":"1","article-title":"Pruning filters for efficient convnets","author":"li","year":"2017","journal-title":"Proc ICLR"},{"key":"ref45","article-title":"Efficient inference of CNNs via channel pruning","author":"zhang","year":"2019","journal-title":"arXiv 1908 03266"},{"key":"ref48","first-page":"646","article-title":"Deep networks with stochastic depth","author":"huang","year":"2016","journal-title":"Proc ECCV"},{"key":"ref47","article-title":"FALCON: Fast and lightweight convolution for compressing and accelerating CNN","author":"quan","year":"2019","journal-title":"arXiv 1909 11321"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref41","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc ICLR"},{"key":"ref44","first-page":"304","article-title":"Data-driven sparse structure selection for deep neural networks","author":"huang","year":"2018","journal-title":"Proc ECCV"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/336"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08935102.pdf?arnumber=8935102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T18:12:41Z","timestamp":1643307161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8935102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2960315","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2019]]}}}