{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T22:29:37Z","timestamp":1793485777437,"version":"4.5.0"},"reference-count":218,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2018R1A2B3008640"],"award-info":[{"award-number":["NRF-2018R1A2B3008640"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning & Evaluation","award":["2020-0-00440"],"award-info":[{"award-number":["2020-0-00440"]}],"id":[{"id":"https:\/\/ror.org\/01g0hqq23","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,6,1]]},"DOI":"10.1109\/tpami.2021.3055564","type":"journal-article","created":{"date-parts":[[2021,1,29]],"date-time":"2021-01-29T16:21:42Z","timestamp":1611937302000},"page":"3048-3068","source":"Crossref","is-referenced-by-count":766,"title":["Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7485-4493","authenticated-orcid":false,"given":"Lin","family":"Wang","sequence":"first","affiliation":[{"name":"Visual Intelligence Laboratory, Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1634-2756","authenticated-orcid":false,"given":"Kuk-Jin","family":"Yoon","sequence":"additional","affiliation":[{"name":"Visual Intelligence Laboratory, Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Conf. Neural Inf. Process. Syst. Deep Learn. Workshop","author":"Hinton"},{"key":"ref2","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1142\/S0218213008004059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00940"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01032"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00938"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054157"},{"key":"ref12","article-title":"Contrastive representation distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tian"},{"key":"ref13","first-page":"2654","article-title":"Do deep nets really need to be deep?","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Ba"},{"key":"ref14","article-title":"On compressing u-net using knowledge distillation","author":"Mangalam","year":"2018"},{"key":"ref15","article-title":"Adaptive regularization of labels","author":"Ding","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/s19194307"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.102"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00297"},{"key":"ref20","article-title":"Knowledge flow: Improve upon your teachers","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref21","article-title":"Apprentice: Using knowledge distillation techniques to improve low-precision network accuracy","author":"Mishra","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.211"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref24","first-page":"2561","article-title":"Positive-unlabeled compression on the cloud","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref25","article-title":"Noisy collaboration in knowledge distillation","author":"Sarfraz","year":"2019","journal-title":"Openreview.net"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1382"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015628"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00302"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10195"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00511"},{"key":"ref32","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Furlanello"},{"key":"ref33","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zagoruyko"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref35","article-title":"Ensemble distribution distillation","author":"Malinin","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00144"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098135"},{"key":"ref39","article-title":"Semi-supervised knowledge transfer for deep learning from private training data","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Papernot"},{"key":"ref40","article-title":"Deep model compression: Distilling knowledge from noisy teachers","author":"Sau","year":"2016"},{"key":"ref41","first-page":"7528","article-title":"Knowledge distillation by on-the-fly native ensemble","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Lan"},{"key":"ref42","first-page":"1832","article-title":"Collaborative learning for deep neural networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Song"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00433"},{"key":"ref44","article-title":"Multilingual neural machine translation with knowledge distillation","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Tan"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00329"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00128"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00382"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371792"},{"key":"ref49","article-title":"Feed: Feature-level ensemble for knowledge distillation","author":"Park"},{"key":"ref50","first-page":"1537","article-title":"Stochasticity and skip connections improve knowledge transfer","volume-title":"Proc. 28th Eur. Signal Process. Conf.","author":"Lee"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5746"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref53","article-title":"Fitnets: Hints for thin deep nets","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Romero"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref55","article-title":"MiniLM: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","author":"Wang","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/app9101966"},{"key":"ref58","first-page":"4723","article-title":"Knowledge transfer with jacobian matching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srinivas"},{"key":"ref59","article-title":"Knowledge projection for effective design of thinner and faster deep neural networks","author":"Zhang","year":"2017"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_21"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014886"},{"key":"ref63","article-title":"Knowledge squeezed adversarial network compression","author":"Changyong","year":"2019"},{"key":"ref64","first-page":"2760","article-title":"Paraphrasing complex network: Network compression via factor transfer","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6229"},{"key":"ref67","article-title":"Like what you like: Knowledge distill via neuron selectivity transfer","author":"Huang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00143"},{"key":"ref69","first-page":"2006","article-title":"Feature-map-level online adversarial knowledge distillation","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Chung"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00507"},{"key":"ref71","article-title":"Residual knowledge distillation","author":"Gao","year":"2020"},{"key":"ref72","article-title":"Data efficient stagewise knowledge distillation","author":"Kulkarni","year":"2019"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref74","first-page":"201","article-title":"The IM algorithm: A variational approach to information maximization","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Barber"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref76","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Goodfellow"},{"key":"ref77","article-title":"Learning similarity preserving representations with neural similarity and context encoders","author":"Horn","year":"2016"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1595"},{"key":"ref79","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2019.101695"},{"key":"ref81","article-title":"Large scale distributed neural network training through online distillation","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Anil"},{"key":"ref82","article-title":"Hydra: Preserving ensemble diversity for model distillation","author":"Tran","year":"2020"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.33682\/gqpj-ac63"},{"key":"ref84","article-title":"Attentive student meets multi-task teacher: Improved knowledge distillation for pretrained models","author":"Liu","year":"2019"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1441"},{"key":"ref86","article-title":"Knowledge distillation from multiple teachers using visual explanations","author":"Mehak","year":"2018"},{"key":"ref87","article-title":"M2KD: Multi-model and multi-level knowledge distillation for incremental learning","volume-title":"Proc. British Mach. Vis. Conf.","author":"Zhou"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371792"},{"key":"ref89","article-title":"Knowledge adaptation: Teaching to adapt","author":"Ruder","year":"2017"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_15"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/158"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-614"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00329"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/298"},{"key":"ref96","first-page":"6016","article-title":"Multi-task zipping via layer-wise neuron sharing","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"He"},{"key":"ref97","article-title":"Distilled hierarchical neural ensembles with adaptive inference cost","author":"Ruiz","year":"2020"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00294"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00360"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013068"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/573"},{"key":"ref102","article-title":"Knowledge concentration: Learning 100k object classifiers in a single CNN","author":"Gao","year":"2017"},{"key":"ref103","article-title":"Policy distillation","author":"Rusu","year":"2016"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/428"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_32"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065701000588"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412615"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.62"},{"key":"ref109","first-page":"7517","article-title":"Knowledge distillation by on-the-fly native ensemble","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref110","article-title":"Data-free knowledge distillation for deep neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Lopes"},{"key":"ref111","first-page":"4743","article-title":"Zero-shot knowledge distillation in deep networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Nayak"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01253"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00361"},{"key":"ref114","article-title":"Data-free adversarial distillation","author":"Fang","year":"2019"},{"key":"ref115","article-title":"Dream distillation: A data-independent model compression framework","volume-title":"Proc. Int. Conf. Mach. Learn. Joint Workshop","author":"Bhardwaj"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00852"},{"key":"ref118","first-page":"2701","article-title":"Knowledge extraction with no observable data","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Yoo"},{"key":"ref119","first-page":"9547","article-title":"Zero-shot knowledge transfer via adversarial belief matching","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Micaelli"},{"key":"ref120","article-title":"Knowledge distillation using unlabeled mismatched images","author":"Kulkarni","year":"2017"},{"key":"ref121","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967289"},{"key":"ref123","article-title":"Inceptionism: Going deeper into neural networks","author":"Mordvintsev","year":"2015"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00376"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01465"},{"key":"ref126","article-title":"Few-shot learning of neural networks from scratch by pseudo example optimization","volume-title":"Proc. British Mach. Vis. Conf.","author":"Kimura"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5718"},{"key":"ref128","first-page":"1257","article-title":"Sparse gaussian processes using pseudo-inputs","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Snelson"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref130","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref131","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Aytar"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00768"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00048"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802909"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8900646"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2963882"},{"key":"ref140","article-title":"A cross-modal distillation network for person re-identification in RGB-depth","author":"Hafner","year":"2018"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.21"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487708"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2019.8909838"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00656"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093307"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_18"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00683"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00834"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_6"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00367"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.3390\/e21040357"},{"key":"ref157","article-title":"MOD: A deep mixture model with online knowledge distillation for large scale video temporal concept localization","author":"Lin"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00306"},{"key":"ref159","article-title":"Self-distillation amplifies regularization in hilbert space","author":"Mobahi","year":"2020","journal-title":"arXiv: 2002.05715"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015565"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-056-4_050"},{"key":"ref162","article-title":"Rethinking data augmentation: Self-supervision and self-distillation","author":"Lee"},{"key":"ref163","first-page":"2888","article-title":"Moonshine: Distilling with cheap convolutions","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Crowley"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"ref166","article-title":"MSD: Multi-self-distillation learning via multi-classifiers within deep neural networks","author":"Luan","year":"2019"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20890-5_19"},{"key":"ref168","article-title":"Revisit knowledge distillation: A teacher-free framework","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Yuan"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412524"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref171","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_30"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01294"},{"key":"ref174","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"Grill","year":"2020"},{"key":"ref175","first-page":"4088","article-title":"Triple generative adversarial nets","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Chongxuan"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01410-2"},{"key":"ref177","first-page":"775","article-title":"KDGAN: Knowledge distillation with generative adversarial networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref178","article-title":"Training shallow and thin networks for acceleration via knowledge distillation with conditional adversarial networks","author":"Xu","year":"2017","journal-title":"Proc. 6th Int. Conf. Learn. Representations"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_37"},{"key":"ref180","article-title":"Teacher-student compression with generative adversarial networks","author":"Liu","year":"2018"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207235"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11667"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462082"},{"key":"ref184","article-title":"Training student networks for acceleration with conditional adversarial networks","volume-title":"Proc. British Mach. Vis. Conf.","author":"Xu"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013771"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016754"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5816"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2983174"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00285"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00935"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2931656"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014886"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"ref194","article-title":"Compressing GANs using knowledge distillation","author":"Aguinaldo","year":"2019"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00533"},{"key":"ref196","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5765"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053986"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00726"},{"key":"ref200","article-title":"Graph-based knowledge distillation by multi-head self-attention network","volume-title":"Proc. British Mach. Vis. Conf.","author":"Lee"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_13"},{"key":"ref202","article-title":"Temporal ensembling for semi-supervised learning","author":"Laine","year":"2017"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00927"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00100"},{"key":"ref205","article-title":"Self-ensembling for visual domain adaptation","author":"French","year":"2017"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00693"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01172"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015581"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00147"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00975"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_34"},{"key":"ref212","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2015"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00542"},{"key":"ref214","article-title":"N2N learning: Network to network compression via policy gradient reinforcement learning","author":"Ashok","year":"2018"},{"key":"ref215","article-title":"Graph representation learning via multi-task knowledge distillation","volume-title":"Proc. 33rd Neural Inf. Process. Syst. Workshop","author":"Ma"},{"key":"ref216","first-page":"2807","article-title":"The limits of squared euclidean distance regularization","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Derezinski"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00442"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00530"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.012"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.72"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9769881\/09340578.pdf?arnumber=9340578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T18:25:57Z","timestamp":1704824757000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9340578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,1]]},"references-count":218,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3055564","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":[[2022,6,1]]}}}