{"id":"https://openalex.org/W4405029416","doi":"https://doi.org/10.1109/iccv51701.2025.00157","title":"Verbalized Representation Learning for Interpretable Few-Shot Generalization","display_name":"Verbalized Representation Learning for Interpretable Few-Shot Generalization","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405029416","doi":"https://doi.org/10.1109/iccv51701.2025.00157"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.18651","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103056761","display_name":"Cheng-Fu Yang","orcid":"https://orcid.org/0000-0002-6916-2142"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng-Fu Yang","raw_affiliation_strings":["University of California,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110195053","display_name":"Da Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Da Yin","raw_affiliation_strings":["University of California,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058191990","display_name":"Wenbo Hu","orcid":"https://orcid.org/0000-0002-0639-2012"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenbo Hu","raw_affiliation_strings":["University of California,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Heng Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Ji","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030248499","display_name":"Nanyun Peng","orcid":"https://orcid.org/0000-0002-8509-6595"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nanyun Peng","raw_affiliation_strings":["University of California,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033444412","display_name":"Bolei Zhou","orcid":"https://orcid.org/0000-0003-4030-0684"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bolei Zhou","raw_affiliation_strings":["University of California,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087096372","display_name":"Kai-Wei Chang","orcid":"https://orcid.org/0000-0001-5365-0072"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":["University of California,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"1602","last_page":"1612"},"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":0.9164999723434448,"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":0.9164999723434448,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9085999727249146,"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/generalization","display_name":"Generalization","score":0.7994316220283508},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7438903450965881},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7052592039108276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115007162094116},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.5017330646514893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4979729652404785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.403106689453125},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3529733121395111},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2572612762451172},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11604577302932739},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.08315694332122803},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.07839268445968628},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.06203216314315796},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05120152235031128},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.0485919713973999}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7994316220283508},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7438903450965881},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7052592039108276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115007162094116},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.5017330646514893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4979729652404785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.403106689453125},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3529733121395111},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2572612762451172},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11604577302932739},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.08315694332122803},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.07839268445968628},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.06203216314315796},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05120152235031128},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0485919713973999},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.18651","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.18651","pdf_url":"https://arxiv.org/pdf/2411.18651","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.18651","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.18651","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.18651","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.18651","pdf_url":"https://arxiv.org/pdf/2411.18651","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5714225502","display_name":null,"funder_award_id":"N00014-23-1-2780","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320317469","display_name":"Apple","ror":"https://ror.org/059hsda18"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"Humans":[0],"recognize":[1],"objects":[2],"after":[3],"observing":[4],"only":[5],"a":[6,9,44,75,132,146,160],"few":[7],"examples,":[8],"remarkable":[10],"capability":[11],"enabled":[12],"by":[13,73,157],"their":[14],"inherent":[15],"language":[16,72],"understanding":[17],"of":[18,70],"the":[19,68,91,104,126,154],"real-world":[20],"environment.":[21],"Developing":[22],"verbalized":[23,95],"and":[24,64,87,116,145],"interpretable":[25],"representation":[26],"can":[27,110],"significantly":[28],"improve":[29],"model":[30,128],"generalization":[31],"in":[32,67],"low-data":[33],"settings.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"propose":[39],"Verbalized":[40],"Representation":[41],"Learning":[42],"(VRL),":[43],"novel":[45],"approach":[46],"for":[47,52,166],"automatically":[48],"extracting":[49],"human-interpretable":[50],"features":[51,83,96,155],"object":[53],"recognition":[54],"using":[55,141],"few-shot":[56],"data.":[57],"Our":[58],"method":[59],"uniquely":[60],"captures":[61],"inter-class":[62],"differences":[63],"intra-class":[65],"commonalities":[66],"form":[69],"natural":[71],"employing":[74],"Vision-Language":[76],"Model":[77],"(VLM)":[78],"to":[79,100,114,151],"identify":[80],"key":[81],"discriminative":[82],"between":[84],"different":[85],"classes":[86],"shared":[88],"characteristics":[89],"within":[90],"same":[92,127],"class.":[93],"These":[94],"are":[97],"then":[98],"mapped":[99],"numeric":[101],"vectors":[102,109],"through":[103],"VLM.":[105],"The":[106],"resulting":[107],"feature":[108],"be":[111],"further":[112],"utilized":[113],"train":[115],"infer":[117],"with":[118],"downstream":[119,167],"classifiers.":[120],"Experimental":[121],"results":[122],"show":[123],"that,":[124],"at":[125],"scale,":[129],"VRL":[130,158],"achieves":[131],"24%":[133],"absolute":[134,162],"improvement":[135],"over":[136],"prior":[137],"state-of-the-art":[138],"methods":[139],"while":[140],"95%":[142],"less":[143],"data":[144],"smaller":[147],"mode.":[148],"Furthermore,":[149],"compared":[150],"human-labeled":[152],"attributes,":[153],"learned":[156],"exhibit":[159],"20%":[161],"gain":[163],"when":[164],"used":[165],"classification":[168],"tasks.":[169],"Code":[170],"is":[171],"available":[172],"at:":[173],"https://github.com/joeyy5588/VRL/tree/main.":[174]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}