{"id":"https://openalex.org/W3160186419","doi":"https://doi.org/10.1109/icpr48806.2021.9413033","title":"Stochastic Label Refinery: Toward Better Target Label Distribution","display_name":"Stochastic Label Refinery: Toward Better Target Label Distribution","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3160186419","doi":"https://doi.org/10.1109/icpr48806.2021.9413033","mag":"3160186419"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9413033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413033","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/A5056154880","display_name":"Xi Fang","orcid":"https://orcid.org/0000-0002-3202-8708"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xi Fang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020501435","display_name":"Jiancheng Yang","orcid":"https://orcid.org/0000-0003-4455-7145"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiancheng Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014362734","display_name":"Bingbing Ni","orcid":"https://orcid.org/0000-0001-7339-028X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingbing Ni","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056154880"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61323979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"9115","last_page":"9121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9980999827384949,"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":0.9980999827384949,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9962000250816345,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9718999862670898,"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/refinery","display_name":"Refinery","score":0.6473291516304016},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.556588351726532},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5460375547409058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.327190101146698},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1872689425945282},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.17814266681671143},{"id":"https://openalex.org/keywords/environmental-engineering","display_name":"Environmental engineering","score":0.05773809552192688}],"concepts":[{"id":"https://openalex.org/C105168734","wikidata":"https://www.wikidata.org/wiki/Q1867977","display_name":"Refinery","level":2,"score":0.6473291516304016},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.556588351726532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5460375547409058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.327190101146698},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1872689425945282},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.17814266681671143},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.05773809552192688},{"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:10.1109/icpr48806.2021.9413033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413033","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":[{"id":"https://openalex.org/G4355982842","display_name":null,"funder_award_id":"U20B200011,61976137","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1529808766","https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W2033872649","https://openalex.org/W2064236088","https://openalex.org/W2101210369","https://openalex.org/W2102539288","https://openalex.org/W2108598243","https://openalex.org/W2111316763","https://openalex.org/W2132221661","https://openalex.org/W2151058089","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2549139847","https://openalex.org/W2581377246","https://openalex.org/W2620998106","https://openalex.org/W2626967530","https://openalex.org/W2746314669","https://openalex.org/W2747685395","https://openalex.org/W2747909401","https://openalex.org/W2752782242","https://openalex.org/W2768282280","https://openalex.org/W2795587607","https://openalex.org/W2802198257","https://openalex.org/W2948210185","https://openalex.org/W2949736877","https://openalex.org/W2955425717","https://openalex.org/W2963173418","https://openalex.org/W2963351448","https://openalex.org/W2963420686","https://openalex.org/W2963446712","https://openalex.org/W2963516811","https://openalex.org/W2963587345","https://openalex.org/W2963588253","https://openalex.org/W2963855133","https://openalex.org/W2964212410","https://openalex.org/W2970206392","https://openalex.org/W2975761646","https://openalex.org/W2998508940","https://openalex.org/W3035160371","https://openalex.org/W3118608800","https://openalex.org/W3180562345","https://openalex.org/W4297798436","https://openalex.org/W6637373629","https://openalex.org/W6638523607","https://openalex.org/W6681686657","https://openalex.org/W6732696085","https://openalex.org/W6739651123","https://openalex.org/W6743428213","https://openalex.org/W6743440100","https://openalex.org/W6749107692","https://openalex.org/W6751444130","https://openalex.org/W6762718338","https://openalex.org/W6763882748","https://openalex.org/W6768297763","https://openalex.org/W6770592442","https://openalex.org/W6775876232"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2362901847","https://openalex.org/W4237098069","https://openalex.org/W2380470958","https://openalex.org/W2183714257","https://openalex.org/W2608364297","https://openalex.org/W2463984756","https://openalex.org/W4236884213","https://openalex.org/W4368340790"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,28,204],"simple":[4],"yet":[5],"effective":[6],"strategy":[7],"for":[8,85],"improving":[9],"deep":[10],"supervised":[11],"learning,":[12],"named":[13],"Stochastic":[14],"Label":[15],"Refinery":[16],"(SLR),":[17],"by":[18],"refining":[19],"training":[20,27,86,136],"labels":[21],"to":[22,92,127,169,200,217],"more":[23],"informative":[24],"labels.":[25],"When":[26],"neural":[29,88],"network,":[30],"target":[31,41,56,76,82,97,109,130,142,165],"distributions":[32,57,84,98,110,131,143],"(or":[33],"ground-truth)":[34],"are":[35,99,115,125,144],"typically":[36],"\u201chard\u201d,":[37],"which":[38,90],"means":[39],"the":[40,53,74,87,107,112,123,129,141,163,190],"label":[42,83],"of":[43,47,72,135],"each":[44],"category":[45],"consists":[46],"only":[48],"0":[49],"and":[50,111,156,202,219],"1.":[51],"However,":[52],"fixed":[54],"\u201chard\u201d":[55],"do":[58],"not":[59],"capture":[60],"association":[61],"between":[62,66],"categories":[63],"or":[64],"that":[65,162],"objects.":[67],"In":[68,120,138],"this":[69],"study,":[70],"instead":[71],"using":[73],"hard":[75],"distributions,":[77],"we":[78],"iteratively":[79],"generate":[80],"\u201csoft\u201d":[81],"networks,":[89],"leads":[91,168],"better":[93],"performances.":[94],"The":[95,211],"soft":[96],"obtained":[100],"via":[101],"an":[102],"Expectation-Maximization":[103],"(EM)":[104],"iteration,":[105],"where":[106],"\u201ctrue\u201d":[108],"learned":[113],"models":[114,124],"regarded":[116],"as":[117],"hidden":[118],"variables.":[119],"E":[121],"step,":[122,140],"optimized":[126],"approximate":[128],"on":[132,149,154,175,194,207],"stochastic":[133],"splits":[134],"data;":[137],"M":[139],"updated":[145],"with":[146],"predicted":[147],"pseudo-label":[148],"leave-out":[150],"splits.":[151],"Extensive":[152],"experiments":[153],"classification":[155],"ordinal":[157],"regression":[158],"tasks,":[159],"empirically":[160],"prove":[161],"refined":[164],"distribution":[166],"consistently":[167],"considerable":[170],"performance":[171],"improvements":[172],"even":[173],"applied":[174],"competitive":[176],"baselines.":[177],"Notably,":[178],"in":[179],"DeepDR":[180],"2020":[181],"Diabetic":[182],"Retinopathy":[183],"Grading":[184],"(DeepDRiD)":[185],"challenge,":[186],"our":[187],"method":[188],"improves":[189],"quadratic":[191],"weighted":[192],"kappa":[193],"official":[195],"validation":[196],"set":[197],"from":[198],"0.8247":[199],"0.8348":[201],"achieves":[203],"state-of-the-art":[205],"score":[206],"online":[208],"test":[209],"set.":[210],"proposed":[212],"SLR":[213],"technique":[214],"is":[215],"easy":[216],"implement":[218],"practically":[220],"applicable.":[221]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}