{"id":"https://openalex.org/W7162654492","doi":"https://doi.org/10.48550/arxiv.2605.28809","title":"AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning","display_name":"AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162654492","doi":"https://doi.org/10.48550/arxiv.2605.28809"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.28809","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28809","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.28809","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124935476","display_name":"Zhen-Hao Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Zhen-Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000905854","display_name":"Yu-Cheng Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yu-Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137238539","display_name":"Da-Wei Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Da-Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.8435999751091003,"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":0.8435999751091003,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.04179999977350235,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.01140000019222498,"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/representation","display_name":"Representation (politics)","score":0.5759000182151794},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5116999745368958},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4893999993801117},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48170000314712524},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.47530001401901245},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47279998660087585},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.45190000534057617},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.45159998536109924},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.4318999946117401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264000177383423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118999719619751},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5759000182151794},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5116999745368958},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45159998536109924},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.4318999946117401},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3971000015735626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39660000801086426},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35929998755455017},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C160697094","wikidata":"https://www.wikidata.org/wiki/Q1233197","display_name":"Oblique case","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C165818556","wikidata":"https://www.wikidata.org/wiki/Q213488","display_name":"Geodesic","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C75814411","wikidata":"https://www.wikidata.org/wiki/Q4818714","display_name":"Attribute domain","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.28809","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28809","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.28809","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28809","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Class-Incremental":[0],"Learning":[1],"(CIL)":[2],"is":[3,102,196],"important":[4],"in":[5,89,129],"building":[6],"real-world":[7],"learning":[8,69],"systems.":[9],"In":[10],"CLIP-based":[11,130],"CIL,":[12],"the":[13,75,90,99,143],"model":[14,56,76],"performs":[15],"classification":[16],"by":[17,165],"comparing":[18],"similarity":[19],"between":[20],"visual":[21,138],"and":[22,50,66,83,111,127,139,161],"textual":[23,140],"embeddings":[24],"obtained":[25],"from":[26,98],"template":[27],"prompts,":[28],"e.g.,":[29],"``a":[30],"photo":[31],"of":[32],"a":[33,55,70,166],"[CLASS]''.":[34],"This":[35],"seemingly":[36],"monolithic":[37],"matching":[38],"process":[39],"can":[40,106],"be":[41],"decomposed":[42],"into":[43],"two":[44],"conceptually":[45],"distinct":[46],"stages:":[47],"attribute":[48,51,109,125,178],"extraction":[49,110,126],"aggregation.":[52],"For":[53],"example,":[54],"may":[57],"recognize":[58],"cat":[59],"using":[60],"attributes":[61,80,141],"such":[62],"as":[63],"fur":[64],"texture":[65],"whiskers.":[67],"When":[68],"new":[71,114],"class":[72],"like":[73,81],"car,":[74],"must":[77],"extract":[78],"additional":[79],"wheels":[82],"adjust":[84],"how":[85],"they":[86],"are":[87],"aggregated":[88],"shared":[91],"representation":[92],"space.":[93],"However,":[94],"since":[95],"only":[96],"data":[97],"current":[100],"task":[101,177],"available,":[103],"incremental":[104],"updates":[105],"bias":[107],"both":[108],"aggregation":[112,128],"toward":[113],"classes,":[115],"leading":[116],"to":[117],"catastrophic":[118],"forgetting.":[119],"Therefore,":[120],"we":[121,135,154,173],"propose":[122],"AREA":[123,190],"for":[124,183],"CIL.":[131],"To":[132,151],"stabilize":[133,152],"extraction,":[134],"anchor":[136],"class-level":[137],"on":[142],"hyperspherical":[144],"embedding":[145],"space":[146],"via":[147,180],"principal":[148],"geodesic":[149],"analysis.":[150],"aggregation,":[153],"learn":[155],"lightweight":[156],"task-specific":[157],"experts":[158],"with":[159],"scoring":[160],"residual":[162],"refinement,":[163],"regularized":[164],"variational":[167],"information":[168],"bottleneck":[169],"objective.":[170],"During":[171],"inference,":[172],"perform":[174],"routing":[175],"over":[176],"manifolds":[179],"optimal":[181],"transport":[182],"more":[184],"concise":[185],"prediction.":[186],"Experiments":[187],"show":[188],"that":[189],"consistently":[191],"outperforms":[192],"SOTA":[193],"methods.":[194],"Code":[195],"available":[197],"at":[198],"https://github.com/LAMDA-CL/ICML2026-AREA.":[199]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-29T00:00:00"}