{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:47:36Z","timestamp":1783097256942,"version":"3.54.6"},"reference-count":70,"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":"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"}],"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.2020.2975903","type":"journal-article","created":{"date-parts":[[2020,2,25]],"date-time":"2020-02-25T04:21:31Z","timestamp":1582604491000},"page":"715-726","source":"Crossref","is-referenced-by-count":60,"title":["Universal Deep Neural Network Compression"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4496-0738","authenticated-orcid":false,"given":"Yoojin","family":"Choi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9421-6037","authenticated-orcid":false,"given":"Mostafa","family":"El-Khamy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6132-1786","authenticated-orcid":false,"given":"Jungwon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref70","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"zhu","year":"0","journal-title":"Proc NeurIPS Workshop Compact Deep Neural Netw Representation With Ind Appl"},{"key":"ref39","article-title":"Convolutional neural networks using logarithmic data representation","author":"miyashita","year":"2016"},{"key":"ref38","first-page":"2849","article-title":"Fixed point quantization of deep convolutional networks","author":"lin","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref32","article-title":"Compressing neural networks using the variational information bottleneck","author":"dai","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"2178","article-title":"Runtime neural pruning","author":"lin","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"3290","article-title":"Bayesian compression for deep learning","author":"louizos","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref37","first-page":"1737","article-title":"Deep learning with limited numerical precision","author":"gupta","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","article-title":"Training deep neural networks with low precision multiplications","author":"courbariaux","year":"0","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00339"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1976.tb02943.x"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01340.x"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1984.1056920"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1968.1054193"},{"key":"ref28","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056483"},{"key":"ref27","first-page":"1379","article-title":"Dynamic network surgery for efficient DNNs","author":"guo","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref65","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref66","article-title":"gzip","author":"gailly","year":"2003"},{"key":"ref29","first-page":"2498","article-title":"Variational dropout sparsifies deep neural networks","author":"molchanov","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref67","article-title":"bzip2","author":"seward","year":"1998"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref69","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2975903"},{"key":"ref1","article-title":"Towards the limit of network quantization","author":"choi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref20","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":"ref22","article-title":"Soft weight-sharing for neural network compression","author":"ullrich","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.761"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2886192"},{"key":"ref23","first-page":"1141","article-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","author":"agustsson","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"0","journal-title":"Advances Neural Inf Process Syst"},{"key":"ref25","article-title":"Compressing deep convolutional networks using vector quantization","author":"gong","year":"2014"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00050"},{"key":"ref51","article-title":"Learning low precision deep neural networks through regularization","author":"choi","year":"2018"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056456"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1972.1054906"},{"key":"ref57","author":"cover","year":"2012","journal-title":"Elements of Information Theory"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref53","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref52","article-title":"SqueezeNet: AlexNet-level accuracy with 50&#x00D7; fewer parameters and < 0.5 MB model size","author":"iandola","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/18.720541"},{"key":"ref40","article-title":"Incremental network quantization: Towards lossless CNNs with low-precision weights","author":"zhou","year":"0","journal-title":"Int Conf Learn Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1979.1056067"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1985.1057034"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/18.119699"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056484"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1977.1055714"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1978.1055934"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MC.1984.1659158"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/18.995542"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/29.17498"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/18.42217"},{"key":"ref7","volume":"159","author":"gersho","year":"2012","journal-title":"Vector Quantization and Signal Compression"},{"key":"ref49","first-page":"722","article-title":"Bi-Real Net: Enhancing the performance of 1-bit CNNs with improved representational capability and advanced training algorithm","author":"liu","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1980.1094577"},{"key":"ref46","article-title":"Trained ternary quantization","author":"zhu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","article-title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"zhou","year":"2016"},{"key":"ref48","article-title":"Loss-aware weight quantization of deep networks","author":"hou","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808319"},{"key":"ref44","first-page":"525","article-title":"XNOR-Net: Imagenet classification using binary convolutional neural networks","author":"rastegari","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref43","first-page":"4107","article-title":"Binarized neural networks","author":"hubara","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9163420\/09007430.pdf?arnumber=9007430","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\/9007430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":70,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2020.2975903","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}