{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T17:54:39Z","timestamp":1776275679177,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["U20A20222"],"award-info":[{"award-number":["U20A20222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LR19F020004"],"award-info":[{"award-number":["LR19F020004"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0107400"],"award-info":[{"award-number":["2020AAA0107400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Scientific Technological Innovation Research Project"},{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3066051","type":"journal-article","created":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T20:07:19Z","timestamp":1616184439000},"page":"4735-4746","source":"Crossref","is-referenced-by-count":48,"title":["ResKD: Residual-Guided Knowledge Distillation"],"prefix":"10.1109","volume":"30","author":[{"given":"Xuewei","family":"Li","sequence":"first","affiliation":[]},{"given":"Songyuan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Bourahla","family":"Omar","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3023-1662","authenticated-orcid":false,"given":"Xi","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Deep model compression: Distilling knowledge from noisy teachers","author":"sau","year":"2016","journal-title":"arXiv 1610 09650"},{"key":"ref38","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"Proc NeurIPS"},{"key":"ref33","article-title":"Like what you like: Knowledge distill via neuron selectivity transfer","author":"huang","year":"2017","journal-title":"arXiv 1707 01219"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00938"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref37","article-title":"Contrastive representation distillation","author":"tian","year":"2019","journal-title":"arXiv 1910 10699"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"ref35","article-title":"Paraphrasing complex network: Network compression via factor transfer","author":"kim","year":"2018","journal-title":"arXiv 1802 04977"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"ref60","article-title":"StacNAS: Towards stable and consistent optimization for differentiable neural architecture search","author":"li","year":"2019","journal-title":"arXiv 1909 11926"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2631887"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298629"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2612827"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref64","article-title":"Not all samples are created equal: Deep learning with importance sampling","author":"katharopoulos","year":"2018","journal-title":"arXiv 1803 00942"},{"key":"ref27","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"2016","journal-title":"arXiv 1612 03928"},{"key":"ref65","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref66","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv 1502 03167"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref67","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","article-title":"Self-training with noisy student improves ImageNet classification","author":"xie","year":"2019","journal-title":"arXiv 1911 04252"},{"key":"ref22","article-title":"Knowledge distillation: A survey","author":"gou","year":"2020","journal-title":"arXiv 2006 05525"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref23","article-title":"AdaSample: Adaptive sampling of hard positives for descriptor learning","author":"zhang","year":"2019","journal-title":"arXiv 1911 12110"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2936742"},{"key":"ref25","first-page":"1","article-title":"FitNets: Hints for thin deep nets","author":"romero","year":"2015","journal-title":"Proc ICLR"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1613\/jair.614"},{"key":"ref51","first-page":"231","article-title":"Neural network ensembles, cross validation, and active learning","author":"krogh","year":"1995","journal-title":"Proc NeurIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3032029"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.253"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.23"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.218"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0667-3"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107761"},{"key":"ref53","first-page":"7528","article-title":"Knowledge distillation by on-the-fly native ensemble","author":"lan","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref52","article-title":"Horizontal and vertical ensemble with deep representation for classification","author":"xie","year":"2013","journal-title":"arXiv 1306 2759"},{"key":"ref10","article-title":"Deep net triage: Analyzing the importance of network layers via structural compression","author":"nowak","year":"2018","journal-title":"arXiv 1801 04651"},{"key":"ref11","first-page":"2893","article-title":"Moonshine: Distilling with cheap convolutions","author":"crowley","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5866"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/384"},{"key":"ref13","article-title":"Knowledge flow: Improve upon your teachers","author":"liu","year":"2019","journal-title":"arXiv 1904 05878"},{"key":"ref14","article-title":"Search for better students to learn distilled knowledge","author":"gu","year":"2020","journal-title":"arXiv 2001 11612"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"ref16","article-title":"SuperMix: Supervising the mixing data augmentation","author":"dabouei","year":"2020","journal-title":"arXiv 2003 05034"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_34"},{"key":"ref18","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref4","article-title":"Fixing the train-test resolution discrepancy: FixEfficientNet","author":"touvron","year":"2020","journal-title":"arXiv 2003 08237"},{"key":"ref3","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"arXiv 1905 11946"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref5","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref8","first-page":"116","article-title":"ShuffleNet V2: Practical guidelines for efficient CNN architecture design","author":"ma","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref49","first-page":"1","article-title":"Ensemble methods in machine learning","author":"dietterich","year":"2000","journal-title":"Proc Int Workshop Multiple Classifier Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref46","article-title":"Improved knowledge distillation via teacher assistant","author":"mirzadeh","year":"2019","journal-title":"arXiv 1902 03393"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00297"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/34.58871"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.10.074"},{"key":"ref42","first-page":"8081","article-title":"Learning to specialize with knowledge distillation for visual question answering","author":"mun","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2995049"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2946102"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6710"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09382121.pdf?arnumber=9382121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:16Z","timestamp":1652194216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9382121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3066051","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}