{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:57:53Z","timestamp":1777658273411,"version":"3.51.4"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1934767"],"award-info":[{"award-number":["1934767"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1934755"],"award-info":[{"award-number":["1934755"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/jstsp.2020.2979669","type":"journal-article","created":{"date-parts":[[2020,3,9]],"date-time":"2020-03-09T19:44:28Z","timestamp":1583783068000},"page":"623-633","source":"Crossref","is-referenced-by-count":69,"title":["Dual Dynamic Inference: Enabling More Efficient, Adaptive, and Controllable Deep Inference"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5889-0729","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2818-1432","authenticated-orcid":false,"given":"Jianghao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting-Kuei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tan","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0721-8999","authenticated-orcid":false,"given":"Richard","family":"Baraniuk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2050-5693","authenticated-orcid":false,"given":"Zhangyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingyan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"GaterNet: Dynamic filter selection in convolutional neural network via a dedicated global gating network","author":"chen","year":"0"},{"key":"ref38","first-page":"2181","article-title":"Runtime neural pruning","author":"lin","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref33","article-title":"A survey of model compression and acceleration for deep neural networks","author":"cheng","year":"2017","journal-title":"arXiv 1710 09282"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00904"},{"key":"ref31","article-title":"Hybrid pruning: Thinner sparse networks for fast inference on edge devices","author":"xu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref30","first-page":"2082","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref37","first-page":"6571","article-title":"Neural ordinary differential equations","author":"chen","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","first-page":"3","article-title":"Convolutional networks with adaptive inference graphs","author":"veit","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00919"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/421"},{"key":"ref29","article-title":"Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers","author":"ye","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref20","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref22","first-page":"4119","article-title":"Tetris: Tile-matching the tremendous irregular sparsity","author":"ji","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080215"},{"key":"ref24","article-title":"Pruning filters for efficient convnets","author":"li","year":"2016","journal-title":"arXiv 1608 08710"},{"key":"ref23","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"molchanov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref51","article-title":"SqueezeNet: Alexnet-level accuracy with 50x fewer parameters and $< $0.5 mb model size","author":"iandola","year":"0","journal-title":"arXiv 1602 07360"},{"key":"ref52","article-title":"Residual networks behave like ensembles of relatively shallow networks","author":"veit","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref10","first-page":"409","article-title":"SkipNet: Learning dynamic routing in convolutional networks","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2017.8050797"},{"key":"ref40","article-title":"Slimmable neural networks","author":"yu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.234"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref17","first-page":"5359","article-title":"Deep $ k$-means: Re-training and parameter sharing with harder cluster assignments for compressing deep convolutions","author":"wu","year":"0","journal-title":"Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00913"},{"key":"ref19","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"ref7","article-title":"One model to learn them all","author":"kaiser","year":"2017","journal-title":"arXiv 1706 05137"},{"key":"ref49","article-title":"Digilent ZedBoard Zynq-7000 ARM\/FPGA SoC Development Board","author":"inc","year":"2019"},{"key":"ref9","article-title":"Multi-scale dense networks for resource efficient image classification","author":"huang","year":"2017","journal-title":"arXiv 1703 09844"},{"key":"ref46","article-title":"EnergyNet: Energy-efficient dynamic inference","author":"wang","year":"2018","journal-title":"NeurIPS CDNNRIA Workshop"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.205"},{"key":"ref48","article-title":"Systolic CNN AcceLErator Simulator (SCALE Sim)","author":"samajdar","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref41","first-page":"8080","article-title":"HydraNets: Specialized dynamic architectures for efficient inference","author":"mullapudi","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2893356"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/4200690\/9163420\/9028245-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9163420\/09028245.pdf?arnumber=9028245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:08:25Z","timestamp":1651079305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9028245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":52,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2020.2979669","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}