{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:49:15Z","timestamp":1781797755303,"version":"3.54.5"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976215"],"award-info":[{"award-number":["61976215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772532"],"award-info":[{"award-number":["61772532"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1109\/tsmc.2020.2972695","type":"journal-article","created":{"date-parts":[[2020,2,25]],"date-time":"2020-02-25T22:19:46Z","timestamp":1582669186000},"page":"5918-5928","source":"Crossref","is-referenced-by-count":11,"title":["Multiscale Multipath Ensemble Convolutional Neural Network"],"prefix":"10.1109","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Achun","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enhui","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc Conf Artif Intell Stat"},{"key":"ref38","first-page":"1","article-title":"Network in network","author":"lin","year":"2014","journal-title":"Proc Conf Learn Represent"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2877154"},{"key":"ref32","first-page":"550","article-title":"Residual networks behave like ensembles of relatively shallow networks","author":"veit","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","first-page":"1","article-title":"IGCV3: Interleaved low-rank group convolutions for efficient deep neural networks","author":"sun","year":"2018","journal-title":"Proc British Mach Vis Conf"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00922"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref35","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.469"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2605159"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref20","article-title":"SqueezeNet: AlexNet-level accuracy with $50\\times$\n fewer parameters and < 0.5 MB model size","author":"iandola","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref21","article-title":"Compressing deep convolutional networks using vector quantization","author":"gong","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref25","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref50","first-page":"1","article-title":"Resnet in resnet: Generalizing residual architectures","author":"targ","year":"2016","journal-title":"Proc Conf Learn Represent"},{"key":"ref51","article-title":"Wide residual network for the tiny imagenet challenge","author":"cordeiro","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref52","article-title":"Pruning filters for efficient convnets","author":"li","year":"2016"},{"key":"ref10","first-page":"883","article-title":"Discrimination-aware channel pruning for deep neural networks","author":"zhuang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref40","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","author":"chen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.456"},{"key":"ref16","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Conf Learn Represent"},{"key":"ref18","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2850149"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2830099"},{"key":"ref6","first-page":"1","article-title":"Compression of deep convolutional neural networks for fast and low power mobile applications","author":"kim","year":"2016","journal-title":"Proc Conf Learn Represent"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2884996"},{"key":"ref8","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","author":"denton","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2502579"},{"key":"ref49","article-title":"On the connection of deep fusion to ensembling","author":"zhao","year":"2016"},{"key":"ref9","first-page":"1379","article-title":"Dynamic network surgery for efficient DNNs","author":"guo","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","article-title":"Deeply-fused nets","author":"wang","year":"2016"},{"key":"ref45","first-page":"28","article-title":"Swapout: Learning an ensemble of deep architectures","author":"singh","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","article-title":"Snapshot ensembles: Train 1, get m for free","author":"huang","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref42","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref44","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/9515329\/09011596.pdf?arnumber=9011596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:11Z","timestamp":1652194391000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9011596\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":53,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2020.2972695","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9]]}}}