{"id":"https://openalex.org/W7134087090","doi":"https://doi.org/10.48550/arxiv.2603.05053","title":"CLIP-driven Zero-shot Learning with Ambiguous Labels","display_name":"CLIP-driven Zero-shot Learning with Ambiguous Labels","publication_year":2026,"publication_date":"2026-03-05","ids":{"openalex":"https://openalex.org/W7134087090","doi":"https://doi.org/10.48550/arxiv.2603.05053"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.05053","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128268118","display_name":"Jinfu Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Jinfu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128225509","display_name":"Jiangnan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiangnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128239125","display_name":"Xiaowen Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Xiaowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028401641","display_name":"Xiaohui Zhong","orcid":"https://orcid.org/0000-0002-7506-1276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Xiaohui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128227723","display_name":"Wenpeng Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Wenpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128269623","display_name":"Linqing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Linqing","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25448768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9609000086784363,"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":0.9609000086784363,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.012000000104308128,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.003000000026077032,"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/discriminative-model","display_name":"Discriminative model","score":0.7300000190734863},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5828999876976013},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5128999948501587},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.47540000081062317},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4528999924659729},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.38760000467300415},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.38359999656677246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7621999979019165},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7300000190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7141000032424927},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5828999876976013},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45899999141693115},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4514000117778778},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.38359999656677246},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.25940001010894775}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.05053","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.05053","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.05053","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":"pmh:doi:10.48550/arxiv.2603.05053","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7866419553756714,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"learning":[1,52],"(ZSL)":[2],"aims":[3],"to":[4,55,63,77,92,99,108],"recognize":[5],"unseen":[6],"classes":[7],"by":[8],"leveraging":[9],"semantic":[10,71,110,135],"information":[11],"from":[12],"seen":[13],"classes,":[14],"but":[15],"most":[16],"existing":[17],"methods":[18],"assume":[19],"accurate":[20],"class":[21],"labels":[22,33,94,119,126],"for":[23],"training":[24,114],"instances.":[25],"However,":[26],"in":[27,130],"real-world":[28],"scenarios,":[29],"noise":[30],"and":[31,66,102,105,123,127,139],"ambiguous":[32],"can":[34],"significantly":[35],"reduce":[36],"the":[37,100,113,117,124,134,148],"performance":[38],"of":[39,137,150],"ZSL.":[40],"To":[41],"address":[42],"this,":[43],"we":[44,60],"propose":[45],"a":[46,70,85],"new":[47],"CLIP-driven":[48],"partial":[49,86],"label":[50,57,67,80,106,128,140],"zero-shot":[51,87],"(CLIP-PZSL)":[53],"framework":[54],"handle":[56],"ambiguity.":[58],"First,":[59],"use":[61],"CLIP":[62],"extract":[64,78],"instance":[65,101,104,138],"features.":[68,141],"Then,":[69],"mining":[72],"block":[73],"fuses":[74],"these":[75],"features":[76],"discriminative":[79],"embeddings.":[81],"We":[82],"also":[83],"introduce":[84],"loss,":[88],"which":[89],"assigns":[90],"weights":[91],"candidate":[93],"based":[95],"on":[96,144],"their":[97],"relevance":[98],"aligns":[103],"embeddings":[107,129],"minimize":[109],"mismatch.":[111],"As":[112],"goes":[115],"on,":[116],"ground-truth":[118],"are":[120],"progressively":[121],"identified,":[122],"refined":[125],"turn":[131],"help":[132],"improve":[133],"alignment":[136],"Comprehensive":[142],"experiments":[143],"several":[145],"datasets":[146],"demonstrate":[147],"advantage":[149],"CLIP-PZSL.":[151]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-07T00:00:00"}