{"id":"https://openalex.org/W7138247914","doi":"https://doi.org/10.1609/aaai.v40i30.39694","title":"PANDA \u2013 Patch and Distribution-Aware Augmentation for Long-Tailed Exemplar-Free Continual Learning","display_name":"PANDA \u2013 Patch and Distribution-Aware Augmentation for Long-Tailed Exemplar-Free Continual Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138247914","doi":"https://doi.org/10.1609/aaai.v40i30.39694"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i30.39694","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i30.39694","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i30.39694","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040750644","display_name":"Siddeshwar Raghavan","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Siddeshwar Raghavan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063620170","display_name":"Jiangpeng He","orcid":"https://orcid.org/0000-0002-8552-9880"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiangpeng He","raw_affiliation_strings":["Department of Computer Science, Indiana University, Bloomington, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Indiana University, Bloomington, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129647959","display_name":"Fengqing Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengqing Zhu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040750644"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46199143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"30","first_page":"25056","last_page":"25064"},"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":0.9398999810218811,"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":0.9398999810218811,"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":0.009700000286102295,"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"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.008200000040233135,"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/task","display_name":"Task (project management)","score":0.6812999844551086},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.35109999775886536},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3208000063896179},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3077000081539154},{"id":"https://openalex.org/keywords/concept-drift","display_name":"Concept drift","score":0.30640000104904175},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.29829999804496765},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.2694000005722046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973999738693237},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6812999844551086},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4853000044822693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40059998631477356},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.30640000104904175},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i30.39694","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i30.39694","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i30.39694","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i30.39694","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Exemplar-Free":[0],"Continual":[1],"Learning":[2],"(EFCL)":[3],"restricts":[4],"the":[5,31,129],"storage":[6],"of":[7,34],"previous":[8],"task":[9,122],"data":[10,36,42],"and":[11,62,69,103,137,146,161],"is":[12],"highly":[13],"susceptible":[14],"to":[15,99,124,152],"catastrophic":[16,163],"forgetting.":[17,164],"While":[18],"pre-trained":[19],"models":[20],"(PTMs)":[21],"are":[22],"increasingly":[23],"leveraged":[24],"for":[25],"EFCL,":[26],"existing":[27,86,155],"methods":[28],"often":[29],"overlook":[30],"inherent":[32],"imbalance":[33],"real-world":[35,41],"distributions.":[37],"We":[38],"discovered":[39],"that":[40,65,82,119],"streams":[43],"commonly":[44],"exhibit":[45],"dual-level":[46],"imbalances,":[47,127],"dataset-level":[48],"distributions":[49,123],"combined":[50],"with":[51,85,141,154],"extreme":[52],"or":[53],"reversed":[54],"skews":[55],"within":[56,109],"individual":[57],"tasks,":[58],"creating":[59],"both":[60],"intra-task":[61],"inter-task":[63,126],"disparities":[64],"hinder":[66],"effective":[67],"learning":[68,140],"generalization.":[70],"To":[71],"address":[72],"these":[73],"challenges,":[74],"we":[75],"propose":[76],"PANDA,":[77],"a":[78,96],"Patch-and-Distribution-Aware":[79],"Augmentation":[80],"framework":[81],"integrates":[83],"seamlessly":[84],"PTM-based":[87,156],"EFCL":[88],"methods.":[89],"PANDA":[90,113],"amplifies":[91],"low-frequency":[92],"classes":[93],"by":[94],"using":[95],"CLIP":[97],"encoder":[98],"identify":[100],"representative":[101],"regions":[102],"transplanting":[104],"those":[105],"into":[106],"frequent-class":[107],"samples":[108,134],"each":[110],"task.":[111],"Furthermore,":[112],"incorporates":[114],"an":[115],"adaptive":[116],"balancing":[117],"strategy":[118],"leverages":[120],"prior":[121],"smooth":[125],"reducing":[128,162],"overall":[130],"gap":[131],"between":[132],"average":[133],"across":[135],"tasks":[136],"enabling":[138],"fairer":[139],"frozen":[142],"PTMs.":[143],"Extensive":[144],"experiments":[145],"ablation":[147],"studies":[148],"demonstrate":[149],"PANDA's":[150],"capability":[151],"work":[153],"CL":[157],"methods,":[158],"improving":[159],"accuracy":[160]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}