{"id":"https://openalex.org/W4281861069","doi":"https://doi.org/10.48550/arxiv.2206.01986","title":"Delving into the Openness of CLIP","display_name":"Delving into the Openness of CLIP","publication_year":2022,"publication_date":"2022-06-04","ids":{"openalex":"https://openalex.org/W4281861069","doi":"https://doi.org/10.48550/arxiv.2206.01986"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2206.01986","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.01986","pdf_url":"https://arxiv.org/pdf/2206.01986","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.01986","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101030723","display_name":"Shuhuai Ren","orcid":"https://orcid.org/0009-0001-9998-864X","observed_orcids":["https://orcid.org/0009-0001-9998-864X"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren, Shuhuai","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440407","display_name":"Lei Li","orcid":"https://orcid.org/0000-0003-3095-9776","observed_orcids":["https://orcid.org/0000-0003-3095-9776"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Lei","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049239373","display_name":"Xuancheng Ren","orcid":"https://orcid.org/0000-0002-6994-2114","observed_orcids":["https://orcid.org/0000-0002-6994-2114","https://orcid.org/0009-0009-6239-1266"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren, Xuancheng","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077075399","display_name":"Guangxiang Zhao","orcid":"https://orcid.org/0000-0002-3046-512X","observed_orcids":["https://orcid.org/0000-0002-3046-512X"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Guangxiang","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sun, Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Xu","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7685999870300293,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7685999870300293,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.20559999346733093,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.01679999940097332,"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/clip","display_name":"CLIP","score":0.9629999995231628},{"id":"https://openalex.org/keywords/zero-shot-image-classification","display_name":"zero-shot image classification","score":0.7710000276565552},{"id":"https://openalex.org/keywords/extensibility","display_name":"extensibility","score":0.800000011920929},{"id":"https://openalex.org/keywords/vocabulary-expansion","display_name":"vocabulary enrichment","score":0.8370000123977661},{"id":"https://openalex.org/keywords/representation-alignment","display_name":"representation alignment","score":0.7789999842643738}],"concepts":[{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7390013933181763},{"id":"https://openalex.org/C84976871","wikidata":"https://www.wikidata.org/wiki/Q2015673","display_name":"Openness to experience","level":2,"score":0.7189962863922119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6898579597473145},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.612008273601532},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5742201209068298},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.558456540107727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5311357378959656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5272378325462341},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5207926630973816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5074672102928162},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4770890176296234},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.45716986060142517},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.4169677495956421},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19442692399024963},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16911113262176514},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14421489834785461},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08523166179656982},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07171764969825745},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2206.01986","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.01986","pdf_url":"https://arxiv.org/pdf/2206.01986","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2206.01986","doi":"https://doi.org/10.48550/arxiv.2206.01986","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.01986","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.01986","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.01986","pdf_url":"https://arxiv.org/pdf/2206.01986","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"study_designs":[],"awards":[{"id":"https://openalex.org/G4370721888","display_name":null,"funder_award_id":"62176002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2007906249","https://openalex.org/W2908605513","https://openalex.org/W2394242862","https://openalex.org/W2360338400","https://openalex.org/W2361665985","https://openalex.org/W2391461404","https://openalex.org/W2377875154","https://openalex.org/W3198929874","https://openalex.org/W2352558001","https://openalex.org/W3215964838"],"abstract_inverted_index":{"Contrastive":[0],"Language-Image":[1],"Pre-training":[2],"(CLIP)":[3],"formulates":[4],"image":[5,165],"classification":[6],"as":[7,45,62,120],"an":[8,39,46,84],"image-to-text":[9],"matching":[10,13],"task,":[11],"i.e.,":[12],"images":[14,37],"to":[15,67,83,87,97,102,150,160],"the":[16,33,55,63,89,121,127,133,144,162,185],"corresponding":[17],"natural":[18],"language":[19],"descriptions":[20],"instead":[21],"of":[22,57,130,135,146,170],"discrete":[23],"category":[24],"IDs.":[25],"This":[26],"allows":[27],"for":[28],"open-vocabulary":[29],"visual":[30],"recognition,":[31],"where":[32],"model":[34],"can":[35],"recognize":[36],"from":[38,132],"open":[40,47,66],"class":[41],"set":[42],"(also":[43],"known":[44],"vocabulary)":[48],"in":[49,70,76],"a":[50,99,158],"zero-shot":[51],"manner.":[52],"However,":[53],"evaluating":[54],"openness":[56,90,147,187],"CLIP-like":[58,110],"models":[59,64,111],"is":[60,148],"challenging,":[61],"are":[65,112],"arbitrary":[68],"vocabulary":[69,92,122],"theory,":[71],"but":[72],"their":[73,117],"accuracy":[74],"varies":[75],"practice.":[77],"To":[78],"address":[79],"this,":[80],"we":[81],"resort":[82],"incremental":[85],"perspective":[86],"assess":[88],"through":[91],"expansions,":[93],"and":[94,116,138,167,178],"define":[95],"extensibility":[96],"measure":[98],"model's":[100],"ability":[101],"handle":[103],"novel":[104,171],"classes.":[105,172],"Our":[106,140],"evaluation":[107],"shows":[108],"that":[109,143,175],"not":[113],"truly":[114],"open,":[115],"performance":[118],"deteriorates":[119],"expands.":[123],"We":[124,173],"further":[125],"dissect":[126],"feature":[128],"space":[129],"CLIP":[131,186],"perspectives":[134],"representation":[136],"alignment":[137],"uniformity.":[139],"investigation":[141,177],"reveals":[142],"overestimation":[145],"due":[149],"confusion":[151],"among":[152],"competing":[153],"text":[154,168],"features,":[155],"rather":[156],"than":[157],"failure":[159],"capture":[161],"similarity":[163],"between":[164],"features":[166,169],"hope":[174],"our":[176],"analysis":[179],"will":[180],"facilitate":[181],"future":[182],"research":[183],"on":[184],"issue.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2025-10-10T00:00:00"}