{"id":"https://openalex.org/W3207706809","doi":"https://doi.org/10.1109/access.2021.3119582","title":"Training Robust Deep Neural Networks on Noisy Labels Using Adaptive Sample Selection With Disagreement","display_name":"Training Robust Deep Neural Networks on Noisy Labels Using Adaptive Sample Selection With Disagreement","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3207706809","doi":"https://doi.org/10.1109/access.2021.3119582","mag":"3207706809"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3119582","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3119582","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09568980.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09568980.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101489042","display_name":"H. Takeda","orcid":"https://orcid.org/0000-0003-0713-6878"},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Takeda","raw_affiliation_strings":["Graduate School of Science and Engineering, Kansai University, 3-3-35 Yamate-cho, Suita-shi, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Kansai University, 3-3-35 Yamate-cho, Suita-shi, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061967814","display_name":"Soh Yoshida","orcid":"https://orcid.org/0000-0003-0237-7461"},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Soh Yoshida","raw_affiliation_strings":["Faculty of Engineering Science, Kansai University, 3-3-35 Yamate-cho, Suita-shi, Osaka, Japan. (e-mail: sohy@kansai-u.ac.jp)","Faculty of Engineering Science, Kansai University, 3-3-35 Yamate-cho, Suita-shi, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering Science, Kansai University, 3-3-35 Yamate-cho, Suita-shi, Osaka, Japan. (e-mail: sohy@kansai-u.ac.jp)","institution_ids":["https://openalex.org/I56624758"]},{"raw_affiliation_string":"Faculty of Engineering Science, Kansai University, 3-3-35 Yamate-cho, Suita-shi, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089184180","display_name":"Mitsuji Muneyasu","orcid":"https://orcid.org/0000-0002-4492-5991"},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mitsuji Muneyasu","raw_affiliation_strings":["Faculty of Engineering Science, Kansai University, 3-3-35 Yamate-cho, Suita-shi, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering Science, Kansai University, 3-3-35 Yamate-cho, Suita-shi, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061967814"],"corresponding_institution_ids":["https://openalex.org/I56624758"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.4079,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69341993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"9","issue":null,"first_page":"141131","last_page":"141143"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9991000294685364,"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":0.9991000294685364,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9871000051498413,"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/computer-science","display_name":"Computer science","score":0.7555719614028931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7022705078125},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6421502828598022},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6313878893852234},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6116078495979309},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.596131443977356},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5080063939094543},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4642788767814636},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4248195290565491}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555719614028931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7022705078125},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6421502828598022},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6313878893852234},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6116078495979309},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.596131443977356},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5080063939094543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4642788767814636},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4248195290565491},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3119582","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3119582","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09568980.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1576c61166b146aa925b8065e95c97bf","is_oa":true,"landing_page_url":"https://doaj.org/article/1576c61166b146aa925b8065e95c97bf","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 141131-141143 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3119582","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3119582","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09568980.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322312","display_name":"Kansai University","ror":"https://ror.org/03xg1f311"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3207706809.pdf","grobid_xml":"https://content.openalex.org/works/W3207706809.grobid-xml"},"referenced_works_count":79,"referenced_works":["https://openalex.org/W136846643","https://openalex.org/W1808888563","https://openalex.org/W1815076433","https://openalex.org/W1921293667","https://openalex.org/W1943722231","https://openalex.org/W1964763677","https://openalex.org/W1972675781","https://openalex.org/W2023443033","https://openalex.org/W2101210369","https://openalex.org/W2121056381","https://openalex.org/W2132984949","https://openalex.org/W2147483361","https://openalex.org/W2149273804","https://openalex.org/W2163605009","https://openalex.org/W2256388387","https://openalex.org/W2302255633","https://openalex.org/W2358876993","https://openalex.org/W2592691248","https://openalex.org/W2622100130","https://openalex.org/W2743200750","https://openalex.org/W2752971446","https://openalex.org/W2767094803","https://openalex.org/W2885593519","https://openalex.org/W2887842788","https://openalex.org/W2943997064","https://openalex.org/W2945007112","https://openalex.org/W2951863938","https://openalex.org/W2953070460","https://openalex.org/W2962762541","https://openalex.org/W2963081269","https://openalex.org/W2963096987","https://openalex.org/W2963160702","https://openalex.org/W2963659419","https://openalex.org/W2964234160","https://openalex.org/W2964274690","https://openalex.org/W2964292098","https://openalex.org/W2964309657","https://openalex.org/W2967052791","https://openalex.org/W2969985801","https://openalex.org/W2978426779","https://openalex.org/W2980017318","https://openalex.org/W2985817549","https://openalex.org/W2988966271","https://openalex.org/W2995315671","https://openalex.org/W2995624272","https://openalex.org/W2996108195","https://openalex.org/W2996667721","https://openalex.org/W3035314656","https://openalex.org/W3137695714","https://openalex.org/W4235505822","https://openalex.org/W4288095202","https://openalex.org/W4295312788","https://openalex.org/W6638545294","https://openalex.org/W6640298173","https://openalex.org/W6678280073","https://openalex.org/W6679390333","https://openalex.org/W6682171051","https://openalex.org/W6684191040","https://openalex.org/W6691895530","https://openalex.org/W6698183232","https://openalex.org/W6733814495","https://openalex.org/W6738471490","https://openalex.org/W6740005241","https://openalex.org/W6742511895","https://openalex.org/W6743885473","https://openalex.org/W6747898760","https://openalex.org/W6753772092","https://openalex.org/W6754029020","https://openalex.org/W6758632346","https://openalex.org/W6762563763","https://openalex.org/W6762892961","https://openalex.org/W6762913911","https://openalex.org/W6763485134","https://openalex.org/W6766978945","https://openalex.org/W6768848008","https://openalex.org/W6771630921","https://openalex.org/W6771936042","https://openalex.org/W6779709574","https://openalex.org/W6996569244"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Learning":[0],"with":[1,59,240],"noisy":[2,21,38,81,224],"labels":[3,22],"is":[4,23,50,102,164],"one":[5],"of":[6,85,105,145,154,182,190,194,219,244],"the":[7,26,31,44,63,72,75,83,103,109,113,135,139,143,146,151,155,162,173,177,183,188,191,217,220,229],"most":[8],"practical":[9],"but":[10],"challenging":[11],"tasks":[12],"in":[13,134,197,235],"deep":[14,126],"learning.":[15],"One":[16],"promising":[17],"way":[18],"to":[19,24,79,124,215,223,246],"treat":[20],"use":[25],"small-loss":[27,60,93,147],"trick":[28],"based":[29],"on":[30],"memorization":[32],"effect,":[33],"that":[34,54,74,91],"is,":[35],"clean":[36,92],"and":[37,130,179,213],"samples":[39,77,94,106,168],"are":[40],"identified":[41],"by":[42,65,149,166],"observing":[43],"network\u2019s":[45],"loss":[46,152],"during":[47],"training.":[48],"Co-teaching+":[49],"a":[51,198],"state-of-the-art":[52],"method":[53,123,141,222,231],"simultaneously":[55],"trains":[56],"two":[57,110,184],"networks":[58,111,128,185],"selection":[61,122],"using":[62,204],"\u201cupdate":[64],"disagreement\u201d":[66],"strategy;":[67],"however,":[68],"it":[69],"suffers":[70],"from":[71,172],"problem":[73],"selected":[76],"tend":[78],"become":[80],"as":[82],"number":[84],"iterations":[86],"increases.":[87],"This":[88,116],"phenomenon":[89],"means":[90],"will":[95],"be":[96],"biased":[97],"toward":[98],"agreement":[99,180],"data,":[100],"which":[101,108],"set":[104],"for":[107],"have":[112],"same":[114],"prediction.":[115],"paper":[117],"proposes":[118],"an":[119,236],"adaptive":[120],"sample":[121],"train":[125],"neural":[127],"robustly":[129],"prevent":[131],"noise":[132,242],"contamination":[133],"disagreement":[136,174,178],"strategy.":[137],"Specifically,":[138],"proposed":[140,221,230],"calculates":[142],"threshold":[144,171],"criterion":[148],"considering":[150],"distribution":[153],"whole":[156],"batch":[157],"at":[158],"each":[159],"iteration.":[160],"Then,":[161],"network":[163],"backpropagated":[165],"extracting":[167],"below":[169],"this":[170],"data.":[175],"Combining":[176],"data":[181,196],"can":[186],"suppress":[187],"degradation":[189],"true-label":[192],"rate":[193],"training":[195],"mini":[199],"batch.":[200],"Experiments":[201],"were":[202],"conducted":[203],"five":[205],"commonly":[206],"used":[207],"benchmarks,":[208],"MNIST,":[209],"CIFAR-10,":[210],"CIFAR-100,":[211],"NEWS,":[212],"T-ImageNet":[214],"verify":[216],"robustness":[218],"labels.":[225],"The":[226],"results":[227],"show":[228],"improves":[232],"generalization":[233],"performance":[234],"image":[237],"classification":[238],"task":[239],"simulated":[241],"rates":[243],"up":[245],"50%.":[247]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}