{"id":"https://openalex.org/W4413147331","doi":"https://doi.org/10.1109/cvpr52734.2025.01405","title":"Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning","display_name":"Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147331","doi":"https://doi.org/10.1109/cvpr52734.2025.01405"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01405","doi":"https://doi.org/10.1109/cvpr52734.2025.01405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01405","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.11148","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100365641","display_name":"Tian Liu","orcid":"https://orcid.org/0000-0001-8944-6305","observed_orcids":["https://orcid.org/0000-0001-8944-6305"]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian Liu","raw_affiliation_strings":["Texas A&M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101608535","display_name":"Huixin Zhang","orcid":"https://orcid.org/0000-0003-0338-3986","observed_orcids":["https://orcid.org/0000-0003-0338-3986"]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huixin Zhang","raw_affiliation_strings":["Texas A&M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024670621","display_name":"Shubham Parashar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubham Parashar","raw_affiliation_strings":["Texas A&M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066406697","display_name":"Shu Kong","orcid":"https://orcid.org/0000-0002-1362-5937","observed_orcids":["https://orcid.org/0000-0002-1362-5937"]},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Shu Kong","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6955,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9734791,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"15086","last_page":"15097"},"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":0.9990000128746033,"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":0.9990000128746033,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.000699999975040555,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/few-shot-classification","display_name":"few-shot classification","score":0.9829999804496765},{"id":"https://openalex.org/keywords/retrieval-augmented-learning","display_name":"retrieval-augmented learning","score":0.9240000247955322},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9459999799728394},{"id":"https://openalex.org/keywords/domain-gap","display_name":"domain gap","score":0.5059999823570251},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.6019999980926514},{"id":"https://openalex.org/keywords/zero-shot-recognition","display_name":"zero-shot recognition","score":0.628000020980835},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.5429999828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746874094009399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5786862969398499},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5154502987861633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38810789585113525},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33211344480514526},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06173238158226013},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01405","doi":"https://doi.org/10.1109/cvpr52734.2025.01405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01405","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.11148","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.11148","pdf_url":"https://arxiv.org/pdf/2406.11148","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,"listed_in":[],"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.2406.11148","doi":"https://doi.org/10.48550/arxiv.2406.11148","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.11148","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.11148","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.11148","pdf_url":"https://arxiv.org/pdf/2406.11148","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,"listed_in":[],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G126816581","display_name":null,"funder_award_id":"0067/2024/ITP2","funder_id":"https://openalex.org/F4320323893","funder_display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia"},{"id":"https://openalex.org/G243174938","display_name":null,"funder_award_id":"SRG2023-00044-FST","funder_id":"https://openalex.org/F4320322841","funder_display_name":"Universidade de Macau"},{"id":"https://openalex.org/G8627908586","display_name":null,"funder_award_id":"SRG2023-00044-FST","funder_id":"https://openalex.org/F4320334350","funder_display_name":"High Performance Research Computing, Texas A and M University"}],"funders":[{"id":"https://openalex.org/F4320322841","display_name":"Universidade de Macau","ror":"https://ror.org/01r4q9n85"},{"id":"https://openalex.org/F4320323893","display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia","ror":"https://ror.org/05vna4324"},{"id":"https://openalex.org/F4320334350","display_name":"High Performance Research Computing, Texas A and M University","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413147331.pdf","grobid_xml":"https://content.openalex.org/works/W4413147331.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W153185079","https://openalex.org/W1977295328","https://openalex.org/W2031342017","https://openalex.org/W2047643928","https://openalex.org/W2062118960","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2441255125","https://openalex.org/W2533598788","https://openalex.org/W2795124604","https://openalex.org/W2804935296","https://openalex.org/W2901458284","https://openalex.org/W2914298543","https://openalex.org/W2943052531","https://openalex.org/W2954996726","https://openalex.org/W2963460174","https://openalex.org/W2963845150","https://openalex.org/W2982065462","https://openalex.org/W2992308087","https://openalex.org/W2993323518","https://openalex.org/W3029869103","https://openalex.org/W3135939397","https://openalex.org/W3176193798","https://openalex.org/W3198377975","https://openalex.org/W3198675127","https://openalex.org/W3215720729","https://openalex.org/W4244387609","https://openalex.org/W4312310776","https://openalex.org/W4312877479","https://openalex.org/W4313175608","https://openalex.org/W4366352743","https://openalex.org/W4382999123","https://openalex.org/W4386057720","https://openalex.org/W4386065512","https://openalex.org/W4386065763","https://openalex.org/W4386071547","https://openalex.org/W4386075713","https://openalex.org/W4386075788","https://openalex.org/W4386075975","https://openalex.org/W4386075985","https://openalex.org/W4386076681","https://openalex.org/W4386790226","https://openalex.org/W4390873714","https://openalex.org/W4402569004","https://openalex.org/W4402704589","https://openalex.org/W4402727384","https://openalex.org/W4402727780","https://openalex.org/W4402754286","https://openalex.org/W4410659598"],"related_works":["https://openalex.org/W4416076288","https://openalex.org/W4413156096","https://openalex.org/W4417295232","https://openalex.org/W4409367425","https://openalex.org/W7138125905","https://openalex.org/W7214014614","https://openalex.org/W7170075273","https://openalex.org/W4224261492","https://openalex.org/W4403791743","https://openalex.org/W4316660800"],"abstract_inverted_index":{"Few-shot":[0],"recognition":[1,73],"(FSR)":[2],"aims":[3],"to":[4,34,59,82,115,168],"train":[5],"a":[6,11,20,39,99,102,142],"classification":[7],"model":[8],"with":[9,126],"only":[10],"few":[12],"labeled":[13],"examples":[14,129,147],"of":[15,105,119,158],"each":[16],"concept":[17],"concerned":[18],"by":[19,37,219],"downstream":[21,65,132],"task,":[22],"where":[23],"data":[24,107,121,162,189,201],"annotation":[25],"cost":[26],"can":[27],"be":[28],"prohibitively":[29],"high.":[30],"We":[31,44],"develop":[32],"methods":[33,218],"solve":[35],"FSR":[36,83,151],"leveraging":[38],"pretrained":[40],"Vision-Language":[41],"Model":[42],"(VLM).":[43],"particularly":[45],"explore":[46],"retrieval-augmented":[47],"learning":[48],"(RAL),":[49],"which":[50,183],"retrieves":[51],"open":[52],"data,":[53],"e.g.,":[54],"the":[55,116,127,131,156,170,191,196,199,203],"VLM\u2019s":[56],"pre-training":[57],"dataset,":[58],"learn":[60],"models":[61],"for":[62],"better":[63,165],"serving":[64],"tasks.":[66],"RAL":[67,81],"has":[68],"been":[69],"studied":[70],"in":[71,77,130,190,202],"zero-shot":[72,110],"but":[74],"remains":[75],"under-explored":[76],"FSR.":[78],"Although":[79],"applying":[80],"may":[84],"seem":[85],"straightforward,":[86],"we":[87,137,177],"observe":[88],"interesting":[89],"and":[90,93,122,153,160,173,194],"novel":[91],"challenges":[92],"opportunities.":[94],"First,":[95],"somewhat":[96],"surprisingly,":[97,136],"finetuning":[98,141,154,186],"VLM":[100,143],"on":[101,145,155,187,198,208],"large":[103],"amount":[104],"retrieved":[106,120,159],"underperforms":[108],"state-of-the-art":[109],"methods.":[111],"This":[112],"is":[113],"due":[114],"imbalanced":[117,171],"distribution":[118,172],"its":[123],"domain":[124,174],"gaps":[125],"few-shot":[128,146,161,200],"task.":[133],"Second,":[134],"more":[135],"find":[138],"that":[139,213],"simply":[140],"solely":[144],"significantly":[148,215],"outperforms":[149,216],"previous":[150,217],"methods,":[152],"mix":[157],"yields":[163],"even":[164],"results.":[166],"Third,":[167],"mitigate":[169],"gap":[175],"issues,":[176],"propose":[178],"Stage-Wise":[179],"retrieval-Augmented":[180],"fineTuning":[181],"(SWAT),":[182],"involves":[184],"end-to-end":[185],"mixed":[188],"first":[192],"stage":[193],"retraining":[195],"classifier":[197],"second":[204],"stage.":[205],"Extensive":[206],"experiments":[207],"nine":[209],"popular":[210],"benchmarks":[211],"demonstrate":[212],"SWAT":[214],">6%":[220],"accuracy.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":7}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2025-10-10T00:00:00"}