{"id":"https://openalex.org/W2972417230","doi":"https://doi.org/10.1109/access.2019.2940653","title":"Making Deep Neural Networks Robust to Label Noise: Cross-Training With a Novel Loss Function","display_name":"Making Deep Neural Networks Robust to Label Noise: Cross-Training With a Novel Loss Function","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2972417230","doi":"https://doi.org/10.1109/access.2019.2940653","mag":"2972417230"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2940653","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2940653","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08834773.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/ielx7/6287639/8600701/08834773.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100763095","display_name":"Zhen Qin","orcid":"https://orcid.org/0000-0001-7857-9719"},"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":"Zhen Qin","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029826575","display_name":"Zhengwen Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengwen Zhang","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101533266","display_name":"Yan Li","orcid":"https://orcid.org/0000-0001-9562-9634"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Li","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9562-9634","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445470","display_name":"Jun Guo","orcid":"https://orcid.org/0000-0001-9045-1339"},"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":"Jun Guo","raw_affiliation_strings":["School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.0122,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82960297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"7","issue":null,"first_page":"130893","last_page":"130902"},"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.996399998664856,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9872999787330627,"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":0.8248607516288757},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6646861433982849},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.657673716545105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6264991760253906},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.6050219535827637},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5976661443710327},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5787704586982727},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5518643260002136},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5430083274841309},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.526482343673706},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4403590261936188},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4253392517566681},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38610681891441345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07384893298149109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248607516288757},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6646861433982849},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.657673716545105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6264991760253906},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.6050219535827637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5976661443710327},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5787704586982727},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5518643260002136},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5430083274841309},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.526482343673706},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4403590261936188},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4253392517566681},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38610681891441345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07384893298149109},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2940653","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2940653","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08834773.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:6de4c9b4338746498316e95347fb1370","is_oa":true,"landing_page_url":"https://doaj.org/article/6de4c9b4338746498316e95347fb1370","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"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 7, Pp 130893-130902 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2940653","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2940653","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08834773.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":[{"id":"https://metadata.un.org/sdg/9","score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G8607756921","display_name":null,"funder_award_id":"61901032","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972417230.pdf","grobid_xml":"https://content.openalex.org/works/W2972417230.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1580256954","https://openalex.org/W1608864735","https://openalex.org/W1677182931","https://openalex.org/W1866072925","https://openalex.org/W1921293667","https://openalex.org/W1975128126","https://openalex.org/W2034841618","https://openalex.org/W2102348129","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2121056381","https://openalex.org/W2132984949","https://openalex.org/W2136688338","https://openalex.org/W2167460663","https://openalex.org/W2194775991","https://openalex.org/W2252268321","https://openalex.org/W2296073425","https://openalex.org/W2606613872","https://openalex.org/W2618574054","https://openalex.org/W2620673134","https://openalex.org/W2682189153","https://openalex.org/W2803187616","https://openalex.org/W2885593519","https://openalex.org/W2910915496","https://openalex.org/W2952250950","https://openalex.org/W2962762068","https://openalex.org/W2962762541","https://openalex.org/W2963096987","https://openalex.org/W2963697299","https://openalex.org/W2963730760","https://openalex.org/W2963759070","https://openalex.org/W2964096266","https://openalex.org/W2964137095","https://openalex.org/W2964292098","https://openalex.org/W3118608800","https://openalex.org/W3137695714","https://openalex.org/W6634797541","https://openalex.org/W6636537247","https://openalex.org/W6639331287","https://openalex.org/W6640298173","https://openalex.org/W6678280073","https://openalex.org/W6679390333","https://openalex.org/W6691441656","https://openalex.org/W6736098614","https://openalex.org/W6737985840","https://openalex.org/W6738763127","https://openalex.org/W6740005241","https://openalex.org/W6751420435","https://openalex.org/W6753772092","https://openalex.org/W6763485134","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2803187616","https://openalex.org/W2963759070","https://openalex.org/W3000197790","https://openalex.org/W4385386361"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4,28,166],"achieved":[5],"astonishing":[6],"results":[7,165],"on":[8,153],"a":[9,17,53,83,148],"variety":[10],"of":[11,20,34,79,95,100,151],"supervised":[12],"learning":[13],"tasks":[14],"owing":[15],"to":[16,38,49,59,62,66,170],"large":[18],"scale":[19],"well-labeled":[21],"training":[22,42],"data.":[23],"However,":[24],"as":[25],"recent":[26],"researches":[27],"pointed":[29],"out,":[30],"the":[31,72,77,98,110,128,164],"generalization":[32],"performance":[33],"DNNs":[35,61],"is":[36,57,86,145],"likely":[37],"sharply":[39],"deteriorate":[40],"when":[41],"data":[43,121],"contains":[44],"label":[45,161],"noise.":[46],"In":[47,113],"order":[48],"address":[50],"this":[51,80,115],"problem,":[52],"novel":[54],"loss":[55,81],"function":[56],"proposed":[58,143],"guide":[60],"pay":[63],"more":[64],"attention":[65],"clean":[67],"samples":[68],"via":[69],"adaptively":[70],"weighing":[71],"traditional":[73],"cross-entropy":[74],"loss.":[75],"Under":[76],"guidance":[78],"function,":[82],"cross-training":[84,130],"strategy":[85],"designed":[87],"by":[88],"leveraging":[89],"two":[90],"synergic":[91],"DNN":[92,135],"models,":[93],"each":[94],"which":[96,132],"plays":[97],"roles":[99],"both":[101],"updating":[102],"its":[103,168],"own":[104],"parameters":[105],"and":[106,124,137,163,174],"generating":[107],"curriculums":[108],"for":[109],"other":[111],"one.":[112],"addition,":[114],"paper":[116],"further":[117],"proposes":[118],"an":[119],"online":[120],"filtration":[122],"mechanism":[123],"integrates":[125],"it":[126],"into":[127],"final":[129],"framework,":[131],"simultaneously":[133],"optimizes":[134],"models":[136],"filters":[138],"out":[139],"noisy":[140],"samples.":[141],"The":[142],"approach":[144],"evaluated":[146],"through":[147],"great":[149],"deal":[150],"experiments":[152],"several":[154],"benchmark":[155],"datasets":[156],"with":[157],"man-made":[158],"or":[159],"real-world":[160],"noise,":[162],"demonstrated":[167],"robustness":[169],"different":[171],"noise":[172,175],"types":[173],"scales.":[176]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}