{"id":"https://openalex.org/W3204785911","doi":"https://doi.org/10.1109/tmm.2021.3115635","title":"TC-Net: Detecting Noisy Labels Via Transform Consistency","display_name":"TC-Net: Detecting Noisy Labels Via Transform Consistency","publication_year":2021,"publication_date":"2021-10-02","ids":{"openalex":"https://openalex.org/W3204785911","doi":"https://doi.org/10.1109/tmm.2021.3115635","mag":"3204785911"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3115635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3115635","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/A5048703380","display_name":"Rumeng Yi","orcid":"https://orcid.org/0000-0003-4450-0317"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rumeng Yi","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005101751","display_name":"Yaping Huang","orcid":"https://orcid.org/0000-0002-4465-372X"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaping Huang","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048703380"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.8398,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79062955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"24","issue":null,"first_page":"4328","last_page":"4341"},"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":0.9926000237464905,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9829999804496765,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.81965172290802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8116635084152222},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7391957640647888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6314409375190735},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5357230305671692},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4353090524673462},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.41688844561576843},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3938441574573517},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3786015510559082},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11716943979263306}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.81965172290802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116635084152222},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7391957640647888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6314409375190735},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5357230305671692},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4353090524673462},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.41688844561576843},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3938441574573517},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3786015510559082},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11716943979263306},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3115635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3115635","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":[{"id":"https://metadata.un.org/sdg/9","score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G6294615064","display_name":null,"funder_award_id":"2019JBZ104","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1514928307","https://openalex.org/W1536680647","https://openalex.org/W1921293667","https://openalex.org/W2295107390","https://openalex.org/W2566079294","https://openalex.org/W2787091153","https://openalex.org/W2798830774","https://openalex.org/W2887842788","https://openalex.org/W2920830204","https://openalex.org/W2948606739","https://openalex.org/W2957702778","https://openalex.org/W2964274690","https://openalex.org/W2978625989","https://openalex.org/W2988966271","https://openalex.org/W3000675402","https://openalex.org/W3020429576","https://openalex.org/W3034185248","https://openalex.org/W3118608800","https://openalex.org/W3154541964","https://openalex.org/W6733814495","https://openalex.org/W6738471490","https://openalex.org/W6747899497","https://openalex.org/W6751647823","https://openalex.org/W6753772092","https://openalex.org/W6758632346","https://openalex.org/W6762161020","https://openalex.org/W6762913911","https://openalex.org/W6764051988","https://openalex.org/W6768848008","https://openalex.org/W6771630921","https://openalex.org/W6779702771","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W2350879319","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W2353865532","https://openalex.org/W4205958290"],"abstract_inverted_index":{"It":[0],"is":[1],"crucial":[2],"to":[3,23,38,49,61,77,145,155,178],"distinguish":[4],"mislabeled":[5],"samples":[6,26,37,64,75,91,144],"for":[7,81,136,183],"dealing":[8],"with":[9,199],"noisy":[10,30,90,104,161],"labels.":[11],"Previous":[12],"methods":[13,46],"such":[14],"as":[15],"\u201cCo-teaching\u201d":[16],"and":[17,32,58,85,124,132,174,195],"\u201cJoCoR\u201d":[18],"introduce":[19],"two":[20,51],"different":[21],"networks":[22,52],"select":[24,142],"clean":[25,36,63,74,201],"out":[27],"of":[28,149,160],"the":[29,40,73,82,86,115,129,133,147,150,157,170,200,207,218],"ones":[31],"only":[33,65],"use":[34],"these":[35,45],"train":[39,50],"deep":[41],"models.":[42],"Different":[43],"from":[44,94],"which":[47,113],"require":[48],"simultaneously,":[53],"we":[54,101,140,163,205],"propose":[55,102],"a":[56,103,165,185,221],"simple":[57],"effective":[59],"method":[60,216],"identify":[62],"using":[66,169],"one":[67],"single":[68],"network.":[69,151],"We":[70,188],"discover":[71],"that":[72],"prefer":[76],"reach":[78],"consistent":[79],"predictions":[80],"original":[83,130],"images":[84,88,131,135],"transformed":[87,134],"while":[89],"usually":[92],"suffer":[93],"inconsistent":[95],"predictions.":[96],"Motivated":[97],"by":[98,168,220],"this":[99],"observation,":[100],"label":[105],"detection":[106],"approach,":[107],"named":[108],"Transform":[109],"Consistency":[110],"Network":[111],"(TC-Net),":[112],"constrains":[114],"transform":[116],"consistency":[117,123],"(":[118],"<italic":[119],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[120],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">i.e.,</i>":[121],"category":[122],"visual":[125],"attention":[126],"consistency)":[127],"between":[128],"network":[137],"training.":[138],"Then":[139],"can":[141],"small-loss":[143],"update":[146],"parameters":[148],"Furthermore,":[152],"in":[153,211],"order":[154],"mitigate":[156],"negative":[158],"influence":[159],"labels,":[162],"design":[164],"classification":[166],"loss":[167],"off-line":[171],"hard":[172],"labels":[173,177],"on-line":[175],"soft":[176],"provide":[179],"more":[180],"reliable":[181],"supervisions":[182],"training":[184],"robust":[186],"model.":[187],"conduct":[189],"comprehensive":[190],"experiments":[191],"on":[192],"CIFAR-10,":[193],"CIFAR-100":[194],"Clothing1M":[196],"datasets.":[197],"Compared":[198],"sample":[202],"selection":[203],"baselines,":[204],"achieve":[206],"state-of-the-art":[208],"performance.":[209],"Especially,":[210],"most":[212],"cases,":[213],"our":[214],"proposed":[215],"outperforms":[217],"baselines":[219],"large":[222],"margin.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}