{"id":"https://openalex.org/W4416214900","doi":"https://doi.org/10.1109/tmm.2025.3632688","title":"Rethinking Class-Incremental Learning From a Dynamic Imbalanced Learning Perspective","display_name":"Rethinking Class-Incremental Learning From a Dynamic Imbalanced Learning Perspective","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416214900","doi":"https://doi.org/10.1109/tmm.2025.3632688"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3632688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632688","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/A5070031492","display_name":"Leyuan Wang","orcid":"https://orcid.org/0000-0003-4084-4470"},"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":"Leyuan Wang","raw_affiliation_strings":["Laboratory of Visual Computing and Intelligent System, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4084-4470","affiliations":[{"raw_affiliation_string":"Laboratory of Visual Computing and Intelligent System, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077408167","display_name":"Liuyu Xiang","orcid":"https://orcid.org/0000-0001-8486-6255"},"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":"Liuyu Xiang","raw_affiliation_strings":["Laboratory of Visual Computing and Intelligent System, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8486-6255","affiliations":[{"raw_affiliation_string":"Laboratory of Visual Computing and Intelligent System, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398969","display_name":"Yunlong Wang","orcid":"https://orcid.org/0000-0002-3535-308X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunlong Wang","raw_affiliation_strings":["New Laboratory of Pattern Recognition, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3535-308X","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition, State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019711261","display_name":"Huijia Wu","orcid":null},"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":"Huijia Wu","raw_affiliation_strings":["Laboratory of Visual Computing and Intelligent System, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Visual Computing and Intelligent System, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huafeng Yang","orcid":"https://orcid.org/0000-0003-0496-4221"},"institutions":[{"id":"https://openalex.org/I4210108109","display_name":"Beijing Enterprises (China)","ror":"https://ror.org/01egb4878","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210108109"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huafeng Yang","raw_affiliation_strings":["Business group of Government and Enterprise, China Telecom Corporation Limited, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0496-4221","affiliations":[{"raw_affiliation_string":"Business group of Government and Enterprise, China Telecom Corporation Limited, Beijing, China","institution_ids":["https://openalex.org/I4210108109"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingqian Liu","orcid":"https://orcid.org/0009-0008-8949-9691"},"institutions":[{"id":"https://openalex.org/I4210108109","display_name":"Beijing Enterprises (China)","ror":"https://ror.org/01egb4878","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210108109"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqian Liu","raw_affiliation_strings":["Business group of Government and Enterprise, China Telecom Corporation Limited, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-8949-9691","affiliations":[{"raw_affiliation_string":"Business group of Government and Enterprise, China Telecom Corporation Limited, Beijing, China","institution_ids":["https://openalex.org/I4210108109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057318866","display_name":"Zhaofeng He","orcid":"https://orcid.org/0000-0002-3433-8435"},"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":"Zhaofeng He","raw_affiliation_strings":["Laboratory of Visual Computing and Intelligent System, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3433-8435","affiliations":[{"raw_affiliation_string":"Laboratory of Visual Computing and Intelligent System, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16413183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"825","last_page":"836"},"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":0.7559999823570251,"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":0.7559999823570251,"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":0.09220000356435776,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.034299999475479126,"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/forgetting","display_name":"Forgetting","score":0.862500011920929},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7024000287055969},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6866999864578247},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6323000192642212},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6050999760627747},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5684999823570251},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5162000060081482},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4519999921321869},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4514000117778778}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.862500011920929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8287000060081482},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7024000287055969},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6866999864578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.663100004196167},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5684999823570251},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5386999845504761},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4212000072002411},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4049000144004822},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C2986563244","wikidata":"https://www.wikidata.org/wiki/Q6822310","display_name":"Learning to learn","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3632688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3632688","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":[],"awards":[{"id":"https://openalex.org/G2805850703","display_name":null,"funder_award_id":"62206012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4800139155","display_name":null,"funder_award_id":"62301066","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7239579613","display_name":null,"funder_award_id":"24JZD040","funder_id":"https://openalex.org/F4320312071","funder_display_name":"Ministry of Education, Libya"},{"id":"https://openalex.org/G8361507201","display_name":null,"funder_award_id":"62176025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G858523971","display_name":null,"funder_award_id":"2023RC72","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8709529125","display_name":null,"funder_award_id":"U21B2045","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320312071","display_name":"Ministry of Education, Libya","ror":"https://ror.org/02w030k33"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1682403713","https://openalex.org/W2018345399","https://openalex.org/W2107327607","https://openalex.org/W2108598243","https://openalex.org/W2560647685","https://openalex.org/W2784163702","https://openalex.org/W2786446225","https://openalex.org/W2884282566","https://openalex.org/W2948734064","https://openalex.org/W2954929116","https://openalex.org/W2963351448","https://openalex.org/W2964189064","https://openalex.org/W3021931813","https://openalex.org/W3034856281","https://openalex.org/W3035524453","https://openalex.org/W3065974826","https://openalex.org/W3144281354","https://openalex.org/W3180392831","https://openalex.org/W3203170887","https://openalex.org/W3204340584","https://openalex.org/W3207854039","https://openalex.org/W4289656127","https://openalex.org/W4296916378","https://openalex.org/W4307464646","https://openalex.org/W4312309344","https://openalex.org/W4312521314","https://openalex.org/W4312724926","https://openalex.org/W4312866014","https://openalex.org/W4313028293","https://openalex.org/W4319299931","https://openalex.org/W4390189977","https://openalex.org/W4390873068","https://openalex.org/W4391305686","https://openalex.org/W4392061606","https://openalex.org/W4396680518","https://openalex.org/W4396877720","https://openalex.org/W4399618322","https://openalex.org/W4400680576","https://openalex.org/W4402092710","https://openalex.org/W4402258922","https://openalex.org/W4402557546","https://openalex.org/W4402727466","https://openalex.org/W4402776071","https://openalex.org/W4403791545"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"suffer":[3],"from":[4,19],"catastrophic":[5],"forgetting":[6,40],"when":[7],"continually":[8],"learning":[9,52,103],"new":[10,35,118,179],"concepts.":[11],"In":[12],"this":[13,17],"paper,":[14],"we":[15,63,78,91,132],"analyze":[16],"problem":[18,176],"a":[20,80],"data":[21,37,169,180],"imbalance":[22,30,48,61],"point":[23],"of":[24,41,82,166,177],"view.":[25],"We":[26,108],"argue":[27],"that":[28,121,137,157],"the":[29,42,46,55,59,101,112,122,138,164,175],"between":[31,115],"old":[32,43,116,168],"task":[33,36,88],"and":[34,72,99,117,129,152],"contributes":[38],"to":[39,96],"tasks.":[44],"Moreover,":[45],"increasing":[47],"ratio":[49],"during":[50],"incremental":[51],"further":[53],"aggravates":[54],"problem.":[56],"To":[57],"address":[58],"dynamic":[60],"issue,":[62],"propose":[64],"Uniform":[65],"Prototype":[66],"Contrastive":[67],"Learning":[68],"(UPCL),":[69],"where":[70],"uniform":[71,84,94],"compact":[73],"features":[74],"are":[75],"learned.":[76],"Specifically,":[77],"generate":[79],"set":[81],"non-learnable":[83],"prototypes":[85,95],"before":[86],"each":[87,97],"starts.":[89],"Then":[90],"assign":[92],"these":[93],"class":[98],"guide":[100],"feature":[102,123],"through":[104,134],"prototype":[105],"contrastive":[106],"learning.":[107],"also":[109,173],"dynamically":[110],"adjust":[111],"relative":[113],"margin":[114],"classes":[119],"so":[120],"distribution":[124],"will":[125],"be":[126],"maintained":[127],"balanced":[128],"compact.":[130],"Finally,":[131],"demonstrate":[133],"extensive":[135],"experiments":[136],"proposed":[139],"method":[140],"achieves":[141],"state-of-the-art":[142],"performance":[143],"on":[144],"several":[145],"benchmark":[146],"including":[147],"CIFAR-100,":[148],"ImageNet-100,":[149],"TinyImageNet,":[150],"Food-101,":[151],"CUB-200.":[153],"Experimental":[154],"results":[155],"show":[156],"our":[158],"approach":[159],"not":[160],"only":[161],"effectively":[162],"addresses":[163],"issue":[165],"imbalanced":[167,178],"in":[170],"memory":[171],"but":[172],"tackles":[174],"distributions.":[181]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}