{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T06:03:00Z","timestamp":1784095380672,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["III-1618134"],"award-info":[{"award-number":["III-1618134"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["III-1526012"],"award-info":[{"award-number":["III-1526012"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1149882"],"award-info":[{"award-number":["IIS-1149882"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1724282"],"award-info":[{"award-number":["IIS-1724282"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-17-1-2175"],"award-info":[{"award-number":["N00014-17-1-2175"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000865","name":"Bill and Melinda Gates Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000865","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004783","name":"SAP North America","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004783","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF TRIPODS","award":["#1740822"],"award-info":[{"award-number":["#1740822"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpami.2019.2918284","type":"journal-article","created":{"date-parts":[[2019,5,23]],"date-time":"2019-05-23T20:54:42Z","timestamp":1558644882000},"page":"8704-8716","source":"Crossref","is-referenced-by-count":450,"title":["Convolutional Networks with Dense Connectivity"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6395-0212","authenticated-orcid":false,"given":"Zhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"UC Berkeley, Berkeley Artificial Intelligence Research, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geoff","family":"Pleiss","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Cornell University, Ithaca, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurens van der","family":"Maaten","sequence":"additional","affiliation":[{"name":"Facebook AI Research, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kilian Q.","family":"Weinberger","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Cornell University, Ithaca, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NIPS Workshop Deep Learn Unsupervised Feature Learn"},{"key":"ref38","article-title":"Fitnets: Hints for thin deep nets","volume":"abs 1412 6550","author":"romero","year":"0","journal-title":"CoRR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00291"},{"key":"ref30","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"},{"key":"ref37","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Tech Rep"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref35","article-title":"Striving for simplicity: The all convolutional net","volume":"abs 1412 6806","author":"springenberg","year":"2014","journal-title":"CoRR"},{"key":"ref34","article-title":"Training deep nets with sublinear memory cost","volume":"abs 1604 6174","author":"chen","year":"2016","journal-title":"CoRR"},{"key":"ref10","article-title":"Bridging the gaps between residual learning, recurrent neural networks and visual cortex","volume":"abs 1604 3640","author":"liao","year":"2016","journal-title":"CoRR"},{"key":"ref40","first-page":"iii-1319","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref11","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc 18th Int Conf Artif Intell Statistics"},{"key":"ref12","first-page":"524","article-title":"The cascade-correlation learning architecture","author":"fahlman","year":"1989","journal-title":"Proc Advances in Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2073482"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298642"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.465"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.144"},{"key":"ref18","first-page":"874","article-title":"Adanet: Adaptive structural learning of artificial neural networks","author":"cortes","year":"2017","journal-title":"Proc 34rd Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.156"},{"key":"ref4","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref27","first-page":"4470","article-title":"Dual path networks","author":"chen","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref6","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statistics"},{"key":"ref29","article-title":"H-denseunet: Hybrid densely connected unet for liver and liver tumor segmentation from ct volumes","volume":"abs 1709 7330","author":"li","year":"2017","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref7","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref9","article-title":"Fractalnet: Ultra-deep neural networks without residuals","volume":"abs 1605 7648","author":"larsson","year":"0","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref46","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 Learning Res"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref48","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and < 0.5 MB model size","volume":"abs 1602 7360","author":"iandola","year":"2016","journal-title":"CoRR"},{"key":"ref22","article-title":"Wide residual networks","volume":"abs 1605 7146","author":"zagoruyko","year":"2016","journal-title":"CoRR"},{"key":"ref47","article-title":"Log-densenet: How to sparsify a densenet","volume":"abs 1711 2","author":"hu","year":"2017","journal-title":"CoRR"},{"key":"ref21","article-title":"Resnet in resnet: Generalizing residual architectures","volume":"abs 1603 8029","author":"targ","year":"2016","journal-title":"CoRR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref24","first-page":"3546","article-title":"Semi-supervised learning with ladder networks","author":"rasmus","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref41","first-page":"3288","article-title":"Convolutional neural networks applied to house numbers digit classification","author":"sermanet","year":"2012","journal-title":"Proc 21st Int Conf Pattern Recognit"},{"key":"ref23","article-title":"Network in network","volume":"abs 1312 4400","author":"lin","year":"0","journal-title":"CoRR"},{"key":"ref44","first-page":"iii-1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc 30th Int Conf Int Conf Mach Learn"},{"key":"ref26","article-title":"Deeply-fused nets","volume":"abs 1605 7716","author":"wang","year":"2016","journal-title":"CoRR"},{"key":"ref43","article-title":"Training and investigating residual nets","author":"gross","year":"2016"},{"key":"ref25","first-page":"2368","article-title":"Deconstructing the ladder network architecture","author":"pezeshki","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/9940447\/8721151-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9940447\/08721151.pdf?arnumber=8721151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:11:30Z","timestamp":1670281890000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8721151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":48,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2918284","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]}}}