{"id":"https://openalex.org/W4210691876","doi":"https://doi.org/10.1587/transinf.2021edp7127","title":"Consistency Regularization on Clean Samples for Learning with Noisy Labels","display_name":"Consistency Regularization on Clean Samples for Learning with Noisy Labels","publication_year":2022,"publication_date":"2022-01-31","ids":{"openalex":"https://openalex.org/W4210691876","doi":"https://doi.org/10.1587/transinf.2021edp7127"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2021edp7127","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7127","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/2/E105.D_2021EDP7127/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/2/E105.D_2021EDP7127/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014224994","display_name":"Yuichiro Nomura","orcid":"https://orcid.org/0000-0003-2716-1608"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuichiro NOMURA","raw_affiliation_strings":["Graduate School of Advanced Science and Engineering, Hiroshima University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Engineering, Hiroshima University","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086456461","display_name":"Takio Kurita","orcid":"https://orcid.org/0000-0003-3982-6750"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takio KURITA","raw_affiliation_strings":["Graduate School of Advanced Science and Engineering, Hiroshima University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Engineering, Hiroshima University","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I113306721"],"apc_list":null,"apc_paid":null,"fwci":0.1312,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48758454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"E105.D","issue":"2","first_page":"387","last_page":"395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9861999750137329,"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/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.9800999760627747,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.9034761786460876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.787805438041687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7294038534164429},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6033987998962402},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5556629300117493},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4758160710334778},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4755244553089142},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4746706485748291},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4574929177761078},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.43211066722869873},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1929766833782196},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16208192706108093}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9034761786460876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787805438041687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7294038534164429},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6033987998962402},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5556629300117493},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4758160710334778},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4755244553089142},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4746706485748291},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4574929177761078},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.43211066722869873},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1929766833782196},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16208192706108093},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2021edp7127","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7127","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/2/E105.D_2021EDP7127/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2021edp7127","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7127","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/2/E105.D_2021EDP7127/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G2705815190","display_name":"Training of deep learning models by introducing prior knowledge","funder_award_id":"21K12049","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4210691876.pdf","grobid_xml":"https://content.openalex.org/works/W4210691876.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1921293667","https://openalex.org/W1972675781","https://openalex.org/W2059471177","https://openalex.org/W2121056381","https://openalex.org/W2250384498","https://openalex.org/W2604156156","https://openalex.org/W2682189153","https://openalex.org/W2752971446","https://openalex.org/W2765407302","https://openalex.org/W2803187616","https://openalex.org/W2803237185","https://openalex.org/W2804077623","https://openalex.org/W2919115771","https://openalex.org/W2941387380","https://openalex.org/W2943865428","https://openalex.org/W2945007112","https://openalex.org/W2949736877","https://openalex.org/W2964274690","https://openalex.org/W2964292098","https://openalex.org/W2967052791","https://openalex.org/W2996108195","https://openalex.org/W3035682985","https://openalex.org/W3039366696","https://openalex.org/W3118608800","https://openalex.org/W3136766697","https://openalex.org/W3175103763"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W1598110435","https://openalex.org/W2548184953","https://openalex.org/W1528914981"],"abstract_inverted_index":{"In":[0],"the":[1,69,85,96,126,136,144,165,172,178,188,204,208,212,220,239,264],"recent":[2,86],"years,":[3],"deep":[4,55],"learning":[5,17,56],"has":[6,93],"achieved":[7],"significant":[8],"results":[9,257],"in":[10,139,159],"various":[11],"areas":[12],"of":[13,22,84,112,162],"machine":[14],"learning.":[15],"Deep":[16],"requires":[18],"a":[19,26,42,54,64,117,140,160],"huge":[20],"amount":[21],"data":[23,29,46],"to":[24,154,164,177,183,202,207,238],"train":[25,171],"model,":[27],"and":[28,103,131,134,151,199,211,225,229,253,255],"collection":[30,47],"techniques":[31,48],"such":[32],"as":[33,129,223],"web":[34],"crawling":[35],"have":[36,147],"been":[37],"developed.":[38],"However,":[39],"there":[40],"is":[41,61,76],"risk":[43,161],"that":[44,258],"these":[45],"may":[49],"generate":[50],"incorrect":[51],"labels.":[52],"If":[53],"model":[57,121,138,174,201,217],"for":[58],"image":[59],"classification":[60,137,173,216],"trained":[62],"on":[63,88,187,251],"dataset":[65,97,128],"with":[66,79,100,105,116,235,246],"noisy":[67,106,249],"labels,":[68],"generalization":[70,233],"performance":[71,234],"significantly":[72],"decreases.":[73],"This":[74],"problem":[75],"called":[77,90],"Learning":[78],"Noisy":[80],"Labels":[81],"(LNL).":[82],"One":[83],"researches":[87],"LNL,":[89],"DivideMix":[91],"[1],":[92],"successfully":[94],"divided":[95,127],"into":[98],"samples":[99,115,133,146,190,221],"clean":[101,224],"labels":[102,107,250],"ones":[104],"by":[108,191],"modeling":[109],"loss":[110,149],"distribution":[111],"all":[113],"training":[114,156],"two-component":[118],"Mixture":[119],"Gaussian":[120],"(GMM).":[122],"Then":[123],"it":[124,230],"treats":[125],"labeled":[130],"unlabeled":[132],"trains":[135],"semi-supervised":[141],"manner.":[142],"Since":[143],"selected":[145,189,222,240],"lower":[148],"values":[150],"are":[152,158,259],"easy":[153],"classify,":[155],"models":[157],"overfitting":[163,176,237],"simple":[166,179],"pattern":[167],"during":[168],"training.":[169],"To":[170],"without":[175],"patterns,":[180],"we":[181],"propose":[182],"introduce":[184],"consistency":[185,194],"regularization":[186,195],"GMM.":[192],"The":[193,215],"perturbs":[196],"input":[197],"images":[198,210],"encourages":[200],"outputs":[203],"same":[205],"value":[206],"perturbed":[209,227],"original":[213],"images.":[214],"simultaneously":[218],"receives":[219],"their":[226],"ones,":[228],"achieves":[231],"higher":[232],"less":[236],"samples.":[241],"We":[242],"evaluated":[243],"our":[244],"method":[245],"synthetically":[247],"generated":[248],"CIFAR-10":[252],"CIFAR-100":[254],"obtained":[256],"comparable":[260],"or":[261],"better":[262],"than":[263],"state-of-the-art":[265],"method.":[266]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}