{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:30Z","timestamp":1760245050012,"version":"3.37.3"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2017YFA0700802"],"award-info":[{"award-number":["2017YFA0700802"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61822603","U1713214","61672306","61572271","61527808"],"award-info":[{"award-number":["61822603","U1713214","61672306","61572271","61527808"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen fundamental research fund","award":["JCYJ20170412170602564"],"award-info":[{"award-number":["JCYJ20170412170602564"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2019,10,1]]},"DOI":"10.1109\/tpami.2018.2878258","type":"journal-article","created":{"date-parts":[[2018,10,26]],"date-time":"2018-10-26T19:48:22Z","timestamp":1540583302000},"page":"2291-2304","source":"Crossref","is-referenced-by-count":32,"title":["Runtime Network Routing for Efficient Image Classification"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3952-8753","authenticated-orcid":false,"given":"Yongming","family":"Rao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6053-4344","authenticated-orcid":false,"given":"Ji","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"2178","article-title":"Runtime neural pruning","author":"lin","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.472"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.48"},{"key":"ref31","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299170"},{"key":"ref36","article-title":"Pruning filters for efficient ConvNets","author":"li","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-017-1029-1"},{"key":"ref34","first-page":"598","article-title":"Optimal brain damage","author":"lecun","year":"1990","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref60","first-page":"4278","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc Int Conf Artif Intell"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref61","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","author":"szegedy","year":"2017","journal-title":"Proc Int Conf Artif Intell"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref28","first-page":"890","article-title":"Timely object recognition","author":"karayev","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref64","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"Neural Netw Mach Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.71"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref67","first-page":"2082","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref68","article-title":"Towards vision-based deep reinforcement learning for robotic motion control","author":"zhang","year":"2015","journal-title":"Proc Asian Conf Refrigeration Air-conditioning"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2502579"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3005348"},{"key":"ref1","first-page":"2549","article-title":"Dynamic capacity networks","author":"almahairi","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref20","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"0","journal-title":"arXiv 1704 04861"},{"key":"ref22","first-page":"646","article-title":"Deep networks with stochastic depth","author":"huang","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"hu","year":"2016","journal-title":"arXiv 1607 03250"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref23","first-page":"7","article-title":"Labeled faces in the wild: A database for studying face recognition in unconstrained environments","author":"huang","year":"2007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref25","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":"ref50","first-page":"525","article-title":"XNOR-Net: ImageNet classification using binary convolutional neural networks","author":"rastegari","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref51","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref59","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc 12th Int Conf Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.446"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.379"},{"key":"ref56","first-page":"1","article-title":"Phoneme probability estimation with dynamic sparsely connected artificial neural networks","volume":"5","author":"str\u00f6m","year":"1997","journal-title":"Free Speech J"},{"key":"ref55","first-page":"3545","article-title":"Deep networks with internal selective attention through feedback connections","author":"stollenga","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref54","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref53","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"shazeer","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref10","article-title":"cuDNN: Efficient primitives for deep learning","author":"chetlur","year":"2014","journal-title":"Arxiv 1410 0759"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/nature14540"},{"key":"ref11","article-title":"Deep sequential neural network","author":"denoyer","year":"2014","journal-title":"Proc Conf Neural Inf Process Syst Workshop"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"ref13","article-title":"Shake-shake regularization","author":"gastaldi","year":"2017","journal-title":"arXiv 1705 07485"},{"key":"ref14","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref16","first-page":"177","article-title":"Comparing biases for minimal network construction with back-propagation","author":"hanson","year":"1989","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref17","first-page":"164","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","author":"hassibi","year":"1993","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref18","first-page":"3149","article-title":"Imitation learning by coaching","author":"he","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","first-page":"747","article-title":"Fast classification using sparse decision DAGs","author":"benbouzid","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.42.10.767"},{"key":"ref6","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"bengio","year":"2013","journal-title":"arXiv 1308 3432"},{"key":"ref5","first-page":"1","article-title":"Conditional computation in neural networks for faster models","author":"bengio","year":"2016","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.286"},{"key":"ref7","first-page":"527","article-title":"Adaptive neural networks for fast test-time prediction","author":"bolukbasi","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref49"},{"key":"ref9","article-title":"The power of sparsity in convolutional neural networks","author":"changpinyo","year":"0","journal-title":"arXiv 1702 06257"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1107"},{"key":"ref45","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"molchanov","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"article-title":"PyTorch: Tensors and dynamic neural networks in python with strong GPU acceleration","year":"2017","author":"paszke","key":"ref48"},{"key":"ref47","article-title":"Changing model behavior at test-time using reinforcement learning","author":"odena","year":"2017","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref41","first-page":"3675","article-title":"Dynamic deep neural networks: Optimizing accuracy-efficiency trade-offs by selective execution","author":"liu","year":"2018","journal-title":"Proc Int Conf Artif Intell"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8824149\/08510920.pdf?arnumber=8510920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:13:55Z","timestamp":1657746835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8510920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,1]]},"references-count":69,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2018.2878258","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2019,10,1]]}}}