{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T14:02:11Z","timestamp":1774533731286,"version":"3.50.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Secretary of Universities and Research","award":["2017SGR-463"],"award-info":[{"award-number":["2017SGR-463"]}]},{"name":"Postdoctoral Fellowship Program Beatriu de Pin\u00f3s","award":["2018-BP-00008"],"award-info":[{"award-number":["2018-BP-00008"]}]},{"name":"Horizon 2020 Program of Research and Innovation of the European Union under the Marie Sklodowska-Curie Grant","award":["801370"],"award-info":[{"award-number":["801370"]}]},{"name":"Spanish Ministry of Economy and Competitiveness and the Fondo Europeo de Desarrollo Regional","award":["RTI2018-095287-B-I00"],"award-info":[{"award-number":["RTI2018-095287-B-I00"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3099952","type":"journal-article","created":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T21:48:32Z","timestamp":1627336112000},"page":"105892-105901","source":"Crossref","is-referenced-by-count":3,"title":["DivNet: Efficient Convolutional Neural Network via Multilevel Hierarchical Architecture Design"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4385-8683","authenticated-orcid":false,"given":"Bachir","family":"Kaddar","sequence":"first","affiliation":[]},{"given":"Hadria","family":"Fizazi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9301-4337","authenticated-orcid":false,"given":"Miguel","family":"Hernandez-Cabronero","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7089-7031","authenticated-orcid":false,"given":"Victor","family":"Sanchez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4729-9292","authenticated-orcid":false,"given":"Joan","family":"Serra-Sagrista","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref38","article-title":"Neural architecture search: A survey","author":"elsken","year":"2018","journal-title":"arXiv 1808 05377"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.71"},{"key":"ref32","article-title":"Flattened convolutional neural networks for feedforward acceleration","author":"jin","year":"2014","journal-title":"arXiv 1412 5474"},{"key":"ref31","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":"ref30","article-title":"Training deep neural networks with low precision multiplications","author":"courbariaux","year":"2014","journal-title":"Arxiv 1412 7024"},{"key":"ref37","first-page":"2902","article-title":"Large-scale evolution of image classifiers","volume":"70","author":"real","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn (ICML)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.154"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref28","article-title":"Speeding-up convolutional neural networks using fine-tuned CP-decomposition","author":"lebedev","year":"2014","journal-title":"arXiv 1412 6553"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref29","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref2","first-page":"2553","article-title":"Deep neural networks for object detection","author":"szegedy","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00990"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"ref22","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or ?1","author":"courbariaux","year":"2016","journal-title":"arXiv 1602 02830 [cs]"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"ref24","first-page":"3123","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"4107","article-title":"Binarized neural networks","author":"hubara","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2015","journal-title":"arXiv 1510 00149 [cs]"},{"key":"ref25","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/s18041229"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451339"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref11","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref40","article-title":"Hierarchical representations for efficient architecture search","author":"liu","year":"2017","journal-title":"arXiv 1711 00436"},{"key":"ref12","first-page":"2148","article-title":"Predicting parameters in deep learning","author":"denil","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref15","first-page":"3","article-title":"Rigid-motion scattering for image classification","volume":"1","author":"sifre","year":"2014"},{"key":"ref16","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv 1502 03167"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref19","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size","author":"iandola","year":"2016","journal-title":"arXiv 1602 07360"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298872"},{"key":"ref6","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref5","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref7","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/s19245541"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv 1603 04467"},{"key":"ref45","author":"krizhevsky","year":"2009","journal-title":"CIFAR-10 and CIFAR-100 Datasets"},{"key":"ref48","article-title":"Pelee: A real-time object detection system on mobile devices","author":"wang","year":"2018","journal-title":"arXiv 1804 06882"},{"key":"ref47","first-page":"1","article-title":"Improving ADAM optimizer","author":"tato","year":"2018","journal-title":"Proc Int Conf Learn Represent Workshop"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.314"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2528821"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09495788.pdf?arnumber=9495788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:12Z","timestamp":1639771032000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9495788\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3099952","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}