{"id":"https://openalex.org/W7163988445","doi":"https://doi.org/10.1145/3748522.3779821","title":"Balanced Online Class-Incremental Learning via Dual Classifiers","display_name":"Balanced Online Class-Incremental Learning via Dual Classifiers","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7163988445","doi":"https://doi.org/10.1145/3748522.3779821"},"language":null,"primary_location":{"id":"doi:10.1145/3748522.3779821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779821","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3748522.3779821","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019798265","display_name":"Shunjie Wen","orcid":"https://orcid.org/0000-0003-4450-8896"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Shunjie Wen","raw_affiliation_strings":["Inha University, Incheon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-4450-8896","affiliations":[{"raw_affiliation_string":"Inha University, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I191879574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041993379","display_name":"Thomas Heinis","orcid":"https://orcid.org/0000-0002-7470-2123"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Heinis","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-7470-2123","affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052393620","display_name":"Dong-Wan Choi","orcid":"https://orcid.org/0000-0003-3122-7518"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Wan Choi","raw_affiliation_strings":["Inha University, Incheon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-3122-7518","affiliations":[{"raw_affiliation_string":"Inha University, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I191879574"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019798265"],"corresponding_institution_ids":["https://openalex.org/I191879574"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.96156543,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1029","last_page":"1037"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9860000014305115,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9860000014305115,"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/T12676","display_name":"Machine Learning and ELM","score":0.0012000000569969416,"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/T11448","display_name":"Face recognition and analysis","score":0.0008999999845400453,"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/dual","display_name":"Dual (grammatical number)","score":0.5866000056266785},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5605999827384949},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5315999984741211},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43299999833106995},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.39730000495910645},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"Incremental learning","score":0.38830000162124634},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.3499999940395355},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.3109000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476000189781189},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6438000202178955},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6237000226974487},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5605999827384949},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.39730000495910645},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.30410000681877136},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3748522.3779821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779821","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3748522.3779821","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779821","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6045271158218384,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2015563892","https://openalex.org/W2037979274","https://openalex.org/W2081580037","https://openalex.org/W2194775991","https://openalex.org/W2594833348","https://openalex.org/W2948734064","https://openalex.org/W3005295611","https://openalex.org/W3034202663","https://openalex.org/W3034856281","https://openalex.org/W3174917907","https://openalex.org/W3175853876","https://openalex.org/W3180392831","https://openalex.org/W4214924370","https://openalex.org/W4312210066","https://openalex.org/W4312232016","https://openalex.org/W4386065719","https://openalex.org/W4387757724","https://openalex.org/W4390874440"],"related_works":[],"abstract_inverted_index":{"Online":[0,123],"class-incremental":[1],"learning":[2,7,125],"(OCIL)":[3],"focuses":[4],"on":[5,58],"gradually":[6],"new":[8,47,161],"classes":[9,27,48,162],"(called":[10,28],"plasticity)":[11],"from":[12,157],"a":[13,18,38,79,84,114],"stream":[14],"of":[15,24,44,193],"data":[16],"in":[17,33,36,101,105,140],"single-pass,":[19],"while":[20,170],"concurrently":[21],"preserving":[22],"knowledge":[23,43,60,104,156,176],"previously":[25],"learned":[26],"stability).":[29],"The":[30],"primary":[31],"challenge":[32,81],"OCIL":[34,107,187,205],"lies":[35],"maintaining":[37],"good":[39],"balance":[40],"between":[41],"the":[42,50,106,168,178,191],"old":[45,159],"and":[46,65,133,160],"within":[49],"continually":[51,102],"updated":[52],"model.":[53],"Most":[54],"existing":[55],"methods":[56,89],"rely":[57],"explicit":[59],"interaction":[61],"through":[62],"experience":[63],"replay,":[64],"often":[66,90],"employ":[67],"exclusive":[68],"training":[69,148],"separation":[70,149],"to":[71,82,99,202],"address":[72],"bias":[73],"problems.":[74],"Nevertheless,":[75],"it":[76],"still":[77],"remains":[78],"big":[80],"achieve":[83,129],"well-balanced":[85],"learner,":[86],"as":[87],"these":[88],"exhibit":[91],"either":[92],"reduced":[93],"plasticity":[94,132],"or":[95],"limited":[96],"stability":[97],"due":[98],"difficulties":[100],"integrating":[103],"setting.":[108],"In":[109],"this":[110],"paper,":[111],"we":[112],"propose":[113],"novel":[115],"replay-based":[116,204],"method,":[117],"called":[118],"Balanced":[119],"Inclusive":[120],"Separation":[121],"for":[122,174],"iNcremental":[124],"(BISON),":[126],"which":[127],"can":[128,163],"both":[130,158],"high":[131],"stability,":[134],"thus":[135],"ensuring":[136],"more":[137,196],"balanced":[138,197],"performance":[139,200],"OCIL.":[141],"Our":[142],"BISON":[143],"method":[144],"proposes":[145],"an":[146],"inclusive":[147],"strategy":[150],"using":[151],"dual":[152],"classifiers":[153],"so":[154],"that":[155],"effectively":[164],"be":[165],"integrated":[166],"into":[167],"model,":[169],"introducing":[171],"implicit":[172],"approaches":[173],"transferring":[175],"across":[177],"two":[179],"classifiers.":[180],"Extensive":[181],"experimental":[182],"evaluations":[183],"over":[184],"three":[185],"widely-used":[186],"benchmark":[188],"datasets":[189],"demonstrate":[190],"superiority":[192],"BISON,":[194],"showing":[195],"yet":[198],"better":[199],"compared":[201],"state-of-the-art":[203],"methods.":[206]},"counts_by_year":[],"updated_date":"2026-06-10T14:10:52.464848","created_date":"2026-06-10T00:00:00"}