{"id":"https://openalex.org/W4297435517","doi":"https://doi.org/10.48550/arxiv.2209.12255","title":"Collaboration of Pre-trained Models Makes Better Few-shot Learner","display_name":"Collaboration of Pre-trained Models Makes Better Few-shot Learner","publication_year":2022,"publication_date":"2022-09-25","ids":{"openalex":"https://openalex.org/W4297435517","doi":"https://doi.org/10.48550/arxiv.2209.12255"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.12255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.12255","pdf_url":"https://arxiv.org/pdf/2209.12255","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.12255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050285051","display_name":"Renrui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Renrui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004554","display_name":"Bohao Li","orcid":"https://orcid.org/0000-0001-7354-2116"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bohao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441570","display_name":"W\u011bi Zh\u0101ng","orcid":"https://orcid.org/0000-0002-1533-6979"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389347","display_name":"Hao Dong","orcid":"https://orcid.org/0000-0002-0132-0239"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100732450","display_name":"Hongsheng Li","orcid":"https://orcid.org/0000-0002-2664-7975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hongsheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362419","display_name":"Peng Gao","orcid":"https://orcid.org/0000-0003-4398-5471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Peng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5050285051"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"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":0.9980000257492065,"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":0.9980000257492065,"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":0.9965000152587891,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646470069885254},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6725056171417236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5962322950363159},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5713903903961182},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5710575580596924},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.454365998506546},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4113353192806244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3829307556152344},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06477931141853333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646470069885254},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6725056171417236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5962322950363159},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5713903903961182},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5710575580596924},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.454365998506546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4113353192806244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3829307556152344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06477931141853333},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2209.12255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.12255","pdf_url":"https://arxiv.org/pdf/2209.12255","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.12255","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.12255","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.12255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.12255","pdf_url":"https://arxiv.org/pdf/2209.12255","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Few-shot":[0],"classification":[1],"requires":[2],"deep":[3],"neural":[4],"networks":[5],"to":[6,122,141,166,179],"learn":[7],"generalized":[8],"representations":[9],"only":[10],"from":[11,32,79,146],"limited":[12],"training":[13,126],"images,":[14],"which":[15],"is":[16],"challenging":[17],"but":[18],"significant":[19],"in":[20,103],"low-data":[21],"regimes.":[22],"Recently,":[23],"CLIP-based":[24],"methods":[25,162],"have":[26],"shown":[27],"promising":[28],"few-shot":[29,50,85,106,125,170],"performance":[30],"benefited":[31],"the":[33,44,49,56,60,124,132,144,157,181],"contrastive":[34],"language-image":[35],"pre-training.":[36],"Based":[37],"on":[38,176],"this":[39,64],"point,":[40],"we":[41,66,115,134],"question":[42],"if":[43],"large-scale":[45],"pre-training":[46,81,161],"can":[47,154],"alleviate":[48],"data":[51,107,127],"deficiency":[52],"and":[53,96,109,148,163,183],"also":[54],"assist":[55],"representation":[57],"learning":[58],"by":[59],"pre-learned":[61],"knowledge.":[62,99],"In":[63],"paper,":[65],"propose":[67],"CoMo,":[68],"a":[69,136],"Collaboration":[70],"of":[71,159,186],"pre-trained":[72],"Models":[73],"that":[74],"incorporates":[75],"diverse":[76,110],"prior":[77],"knowledge":[78,111],"various":[80],"paradigms":[82],"for":[83,169],"better":[84],"learning.":[86],"Our":[87],"CoMo":[88,101,153],"includes:":[89],"CLIP's":[90],"language-contrastive":[91],"knowledge,":[92,95],"DINO's":[93],"vision-contrastive":[94],"DALL-E's":[97],"language-generative":[98],"Specifically,":[100],"works":[102],"two":[104],"aspects:":[105],"expansion":[108],"ensemble.":[112],"For":[113,131],"one,":[114],"generate":[116],"synthetic":[117],"images":[118],"via":[119],"zero-shot":[120],"DALL-E":[121],"enrich":[123],"without":[128],"any":[129],"manpower.":[130],"other,":[133],"introduce":[135],"learnable":[137],"Multi-Knowledge":[138],"Adapter":[139],"(MK-Adapter)":[140],"adaptively":[142],"blend":[143],"predictions":[145],"CLIP":[147],"DINO.":[149],"By":[150],"such":[151],"collaboration,":[152],"fully":[155],"unleash":[156],"potential":[158],"different":[160],"unify":[164],"them":[165],"perform":[167],"state-of-the-art":[168],"classification.":[171],"We":[172],"conduct":[173],"extensive":[174],"experiments":[175],"11":[177],"datasets":[178],"demonstrate":[180],"superiority":[182],"generalization":[184],"ability":[185],"our":[187],"approach.":[188]},"counts_by_year":[{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}