{"id":"https://openalex.org/W3210061328","doi":"https://doi.org/10.1109/tmm.2021.3123478","title":"Dynamic Training Data Dropout for Robust Deep Face Recognition","display_name":"Dynamic Training Data Dropout for Robust Deep Face Recognition","publication_year":2021,"publication_date":"2021-10-27","ids":{"openalex":"https://openalex.org/W3210061328","doi":"https://doi.org/10.1109/tmm.2021.3123478","mag":"3210061328"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3123478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3123478","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028920827","display_name":"Yaoyao Zhong","orcid":"https://orcid.org/0000-0002-2671-9350"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoyao Zhong","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2671-9350","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025452586","display_name":"Weihong Deng","orcid":"https://orcid.org/0000-0001-5952-6996"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihong Deng","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5952-6996","affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032465074","display_name":"Han Fang","orcid":"https://orcid.org/0000-0001-9635-9859"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Fang","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063224243","display_name":"Jiani Hu","orcid":"https://orcid.org/0000-0002-2928-3169"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiani Hu","raw_affiliation_strings":["Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025374137","display_name":"Dongyue Zhao","orcid":"https://orcid.org/0000-0002-0135-0614"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongyue Zhao","raw_affiliation_strings":["Canon Innovative Solution (Beijing) Company, Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0135-0614","affiliations":[{"raw_affiliation_string":"Canon Innovative Solution (Beijing) Company, Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061256224","display_name":"Xian Li","orcid":"https://orcid.org/0000-0002-1509-9328"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xian Li","raw_affiliation_strings":["Canon Innovative Solution (Beijing) Company, Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canon Innovative Solution (Beijing) Company, Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013433372","display_name":"Dongchao Wen","orcid":"https://orcid.org/0000-0001-7311-1842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongchao Wen","raw_affiliation_strings":["Canon Innovative Solution (Beijing) Company, Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7311-1842","affiliations":[{"raw_affiliation_string":"Canon Innovative Solution (Beijing) Company, Ltd., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5524,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.85308301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"1186","last_page":"1197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10828","display_name":"Biometric Identification and Security","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8832511901855469},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8529677987098694},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.7701894044876099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.650284469127655},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.6455252170562744},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5843809843063354},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5371793508529663},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5176035165786743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49291396141052246},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4475541412830353},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4216041564941406},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4122997522354126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40765899419784546},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3405342400074005},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2803848385810852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8832511901855469},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8529677987098694},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.7701894044876099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.650284469127655},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.6455252170562744},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5843809843063354},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5371793508529663},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5176035165786743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49291396141052246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4475541412830353},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4216041564941406},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4122997522354126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40765899419784546},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3405342400074005},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2803848385810852},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3123478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3123478","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G646052229","display_name":null,"funder_award_id":"CX2020201","funder_id":"https://openalex.org/F4320321470","funder_display_name":"Beijing University of Posts and Telecommunications"}],"funders":[{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":92,"referenced_works":["https://openalex.org/W1509966554","https://openalex.org/W1703179648","https://openalex.org/W1949778830","https://openalex.org/W2019464758","https://openalex.org/W2024922353","https://openalex.org/W2095705004","https://openalex.org/W2096733369","https://openalex.org/W2111440402","https://openalex.org/W2140609507","https://openalex.org/W2145287260","https://openalex.org/W2167460663","https://openalex.org/W2186615578","https://openalex.org/W2194775991","https://openalex.org/W2325939864","https://openalex.org/W2404498690","https://openalex.org/W2515770085","https://openalex.org/W2520774990","https://openalex.org/W2557864411","https://openalex.org/W2609575245","https://openalex.org/W2663800299","https://openalex.org/W2737608545","https://openalex.org/W2752782242","https://openalex.org/W2752828042","https://openalex.org/W2781292787","https://openalex.org/W2797558164","https://openalex.org/W2799041689","https://openalex.org/W2871667416","https://openalex.org/W2882991827","https://openalex.org/W2887500939","https://openalex.org/W2891950293","https://openalex.org/W2901505625","https://openalex.org/W2949007385","https://openalex.org/W2955488837","https://openalex.org/W2962895364","https://openalex.org/W2962898354","https://openalex.org/W2963227127","https://openalex.org/W2963460857","https://openalex.org/W2963466847","https://openalex.org/W2963559058","https://openalex.org/W2963671154","https://openalex.org/W2963814162","https://openalex.org/W2963839617","https://openalex.org/W2964155802","https://openalex.org/W2964274690","https://openalex.org/W2964292098","https://openalex.org/W2967637014","https://openalex.org/W2969985801","https://openalex.org/W2970084480","https://openalex.org/W2974328324","https://openalex.org/W2984006054","https://openalex.org/W2985817549","https://openalex.org/W2988966271","https://openalex.org/W2996060033","https://openalex.org/W2997199946","https://openalex.org/W2997312573","https://openalex.org/W3000996870","https://openalex.org/W3034882062","https://openalex.org/W3035325670","https://openalex.org/W3035376925","https://openalex.org/W3094843939","https://openalex.org/W3101227480","https://openalex.org/W3106153666","https://openalex.org/W3109225549","https://openalex.org/W3124054989","https://openalex.org/W3141039124","https://openalex.org/W3175272368","https://openalex.org/W4293478066","https://openalex.org/W4300167309","https://openalex.org/W4301183982","https://openalex.org/W4307823382","https://openalex.org/W6630649318","https://openalex.org/W6637320534","https://openalex.org/W6637373629","https://openalex.org/W6639331287","https://openalex.org/W6640425456","https://openalex.org/W6674330103","https://openalex.org/W6680902425","https://openalex.org/W6681239517","https://openalex.org/W6686509673","https://openalex.org/W6732696085","https://openalex.org/W6735632633","https://openalex.org/W6743885473","https://openalex.org/W6744072679","https://openalex.org/W6747898760","https://openalex.org/W6750318685","https://openalex.org/W6751593755","https://openalex.org/W6751647823","https://openalex.org/W6753410490","https://openalex.org/W6768848008","https://openalex.org/W6773116539","https://openalex.org/W6779482673","https://openalex.org/W6842019321"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3108503355","https://openalex.org/W2249953602","https://openalex.org/W2801655600","https://openalex.org/W2912971006"],"abstract_inverted_index":{"Learning":[0],"with":[1,120],"noise":[2,32,44,67,102,155],"is":[3,110],"a":[4,56,75],"practically":[5],"challenging":[6],"problem":[7],"in":[8,33,45,68,150],"deep":[9,51,146],"face":[10,27,52,147],"recognition.":[11],"Despite":[12],"the":[13,30,34,41,46,66,69,85,89,151],"success":[14],"of":[15,43,92,153],"large":[16,35],"margin":[17],"softmax":[18],"loss":[19,123],"functions,":[20],"these":[21],"methods":[22],"are":[23],"designed":[24],"for":[25,79,114],"clean":[26],"databases.":[28,48],"Considering":[29],"inevitable":[31],"scale":[36],"databases,":[37],"we":[38,54,83],"first":[39],"analyze":[40],"performance":[42],"training":[47,58,70,94],"For":[49],"noise-robust":[50],"recognition,":[53],"propose":[55],"dynamic":[57],"data":[59],"dropout":[60],"(DTDD)":[61],"method":[62,109,142],"to":[63],"dynamically":[64],"filter":[65],"database":[71,78],"and":[72,101,104,112,116,125,133,156],"gradually":[73],"form":[74],"stable":[76,113],"refined":[77],"model":[80,90],"learning.":[81],"Specifically,":[82],"leverage":[84],"information":[86],"provided":[87],"by":[88],"predictions":[91],"accumulated":[93],"epochs,":[95],"which":[96],"can":[97,117,143],"distinguish":[98],"regular":[99],"samples":[100],"effectively":[103],"accurately.":[105],"The":[106],"proposed":[107,141],"DTDD":[108],"easy":[111],"implementation,":[115],"be":[118],"combined":[119],"existing":[121],"state-of-the-art":[122],"functions":[124],"network":[126],"architectures.":[127],"Extensive":[128],"experiments":[129],"on":[130],"CASIA-WebFace,":[131],"VGGFace2,":[132],"MS-Celeb-1":[134],"M":[135],"databases":[136],"empirically":[137],"demonstrate":[138],"that":[139],"our":[140],"robustly":[144],"train":[145],"recognition":[148],"models":[149],"presence":[152],"label":[154],"low":[157],"quality":[158],"images.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}