{"id":"https://openalex.org/W3161990019","doi":"https://doi.org/10.1109/icpr48806.2021.9412550","title":"P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions","display_name":"P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3161990019","doi":"https://doi.org/10.1109/icpr48806.2021.9412550","mag":"3161990019"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-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/A5100727076","display_name":"Wei Hu","orcid":"https://orcid.org/0000-0001-5320-6086"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Hu","raw_affiliation_strings":["Beijing University of Chemical Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053043601","display_name":"Qihao Zhao","orcid":"https://orcid.org/0000-0002-2344-2771"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"QiHao Zhao","raw_affiliation_strings":["Beijing University of Chemical Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005388913","display_name":"Yangyu Huang","orcid":"https://orcid.org/0000-0003-1243-4423"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyu Huang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403428","display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0002-0343-3499"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":["Beijing University of Chemical Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4198,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6841278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1882","last_page":"1889"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9997000098228455,"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":0.9997000098228455,"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/T11220","display_name":"Water Systems and Optimization","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural 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/T12072","display_name":"Machine Learning and Algorithms","score":0.9817000031471252,"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/overfitting","display_name":"Overfitting","score":0.8544601202011108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7159378528594971},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6734440326690674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6632044911384583},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5497102737426758},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5428961515426636},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5271567702293396},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.5091490149497986},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43484070897102356},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41770845651626587},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15695694088935852},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1452893316745758}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8544601202011108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7159378528594971},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6734440326690674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6632044911384583},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5497102737426758},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5428961515426636},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5271567702293396},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.5091490149497986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43484070897102356},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41770845651626587},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15695694088935852},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1452893316745758},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1514928307","https://openalex.org/W1866072925","https://openalex.org/W1866935739","https://openalex.org/W1921293667","https://openalex.org/W1943722231","https://openalex.org/W2027444427","https://openalex.org/W2081613070","https://openalex.org/W2113290770","https://openalex.org/W2132984949","https://openalex.org/W2155893237","https://openalex.org/W2167460663","https://openalex.org/W2287418003","https://openalex.org/W2296073425","https://openalex.org/W2577784528","https://openalex.org/W2592335154","https://openalex.org/W2620673134","https://openalex.org/W2752971446","https://openalex.org/W2795282075","https://openalex.org/W2804077623","https://openalex.org/W2804378530","https://openalex.org/W2884561390","https://openalex.org/W2885593519","https://openalex.org/W2905290040","https://openalex.org/W2909793444","https://openalex.org/W2943997064","https://openalex.org/W2947380870","https://openalex.org/W2951863938","https://openalex.org/W2962762068","https://openalex.org/W2962766164","https://openalex.org/W2963081269","https://openalex.org/W2963096987","https://openalex.org/W2963160702","https://openalex.org/W2963341924","https://openalex.org/W2963371670","https://openalex.org/W2963644303","https://openalex.org/W2963697299","https://openalex.org/W2963735582","https://openalex.org/W2963789034","https://openalex.org/W2964096266","https://openalex.org/W2964155802","https://openalex.org/W2964234160","https://openalex.org/W2964274690","https://openalex.org/W2964292098","https://openalex.org/W2964309657","https://openalex.org/W2973562770","https://openalex.org/W2978625989","https://openalex.org/W2988966271","https://openalex.org/W2990019157","https://openalex.org/W4297813944","https://openalex.org/W6639056814","https://openalex.org/W6639331287","https://openalex.org/W6640298173","https://openalex.org/W6677082149","https://openalex.org/W6679390333","https://openalex.org/W6717697761","https://openalex.org/W6736098614","https://openalex.org/W6737419302","https://openalex.org/W6738763127","https://openalex.org/W6740005241","https://openalex.org/W6742348326","https://openalex.org/W6743885473","https://openalex.org/W6747898760","https://openalex.org/W6750523955","https://openalex.org/W6751647823","https://openalex.org/W6751661576","https://openalex.org/W6751883947","https://openalex.org/W6753772092","https://openalex.org/W6758632346","https://openalex.org/W6762563763"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W2786764570","https://openalex.org/W4309960894","https://openalex.org/W2728804654"],"abstract_inverted_index":{"Learning":[0],"deep":[1],"neural":[2],"network":[3],"(DNN)":[4],"classifier":[5],"with":[6],"noisy":[7,21,54],"labels":[8,22],"is":[9,75,110],"a":[10,33,66],"challenging":[11],"task":[12],"because":[13],"the":[14,50,63,79,83,96,113],"DNN":[15,45],"can":[16,43,87],"easily":[17],"overfit":[18],"on":[19,95,103],"these":[20],"due":[23],"to":[24,69,77,112],"its":[25],"high":[26],"capability.":[27],"In":[28],"this":[29,73],"paper,":[30],"we":[31],"present":[32],"very":[34],"simple":[35],"but":[36,47],"effective":[37],"training":[38,67,84,100],"paradigm":[39],"called":[40],"P-DIFF,":[41],"which":[42],"train":[44],"classifiers":[46],"obviously":[48],"alleviate":[49],"adverse":[51],"impact":[52],"of":[53,65,99],"labels.":[55],"Our":[56],"proposed":[57],"probability":[58,64,74],"difference":[59],"distribution":[60],"implicitly":[61],"reflects":[62],"sample":[68,81,115],"be":[70],"clean,":[71],"then":[72],"employed":[76],"re-weight":[78],"corresponding":[80],"during":[82],"process.":[85],"P-DIFF":[86,109],"also":[88,106],"achieve":[89],"good":[90],"performance":[91],"even":[92],"without":[93],"prior-knowledge":[94],"noise":[97],"rate":[98],"samples.":[101],"Experiments":[102],"benchmark":[104],"datasets":[105],"demonstrate":[107],"that":[108],"superior":[111],"state-of-the-art":[114],"selection":[116],"methods.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}