{"id":"https://openalex.org/W7154152905","doi":"https://doi.org/10.48550/arxiv.2604.09532","title":"Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise","display_name":"Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise","publication_year":2026,"publication_date":"2026-04-10","ids":{"openalex":"https://openalex.org/W7154152905","doi":"https://doi.org/10.48550/arxiv.2604.09532"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.09532","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09532","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.09532","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113412065","display_name":"Zibin Geng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geng, Zibin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133528161","display_name":"Xuefeng Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xuefeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405673","display_name":"Jia Li","orcid":"https://orcid.org/0000-0002-0219-2443"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133492226","display_name":"Zheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133531547","display_name":"Tian Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011623454","display_name":"Lvhua Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Lvhua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133535476","display_name":"Sheng Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Sheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133476897","display_name":"Yuwei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133488675","display_name":"Min Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Min","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":null,"has_fulltext":false,"cited_by_count":0,"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":0.40139999985694885,"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":0.40139999985694885,"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":0.21040000021457672,"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":0.13030000030994415,"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/robustness","display_name":"Robustness (evolution)","score":0.7440999746322632},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5353999733924866},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38989999890327454},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.38960000872612},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3709999918937683},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33739998936653137},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.31700000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928000092506409},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7440999746322632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6046000123023987},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.38960000872612},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.31700000166893005},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.09532","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09532","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.09532","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09532","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Prompt":[0],"learning":[1,57,98],"is":[2,15,38,233],"a":[3,51,65,140,156,201],"parameter-efficient":[4],"approach":[5],"for":[6,59,125],"vision-language":[7],"models,":[8],"yet":[9],"its":[10],"robustness":[11,94,190],"under":[12,31,210],"label":[13,32,42,214],"noise":[14,215],"less":[16],"investigated.":[17],"Visual":[18],"content":[19],"contains":[20],"richer":[21],"and":[22,53,104,164,181,198,212,227],"more":[23,29,157],"reliable":[24],"semantic":[25,162],"information,":[26],"which":[27,154],"remains":[28],"robust":[30,54,158],"noise.":[33,43],"However,":[34],"the":[35,79,89,106,113,118,131,148,173,193],"prompt":[36,56,75,80,97,179],"itself":[37],"highly":[39],"susceptible":[40],"to":[41,69,82,88,99,145],"Motivated":[44],"by":[45,95,116],"this":[46],"intuition,":[47],"we":[48,63,137],"propose":[49],"VisPrompt,":[50],"lightweight":[52,141],"vision-guided":[55],"framework":[58,170],"noisy-label":[60],"settings.":[61],"Specifically,":[62],"exploit":[64],"cross-modal":[66],"attention":[67],"mechanism":[68,144],"reversely":[70],"inject":[71],"visual":[72,85,102,123,135,151],"semantics":[73],"into":[74],"representations.":[76],"This":[77],"enables":[78],"tokens":[81],"selectively":[83],"aggregate":[84],"information":[86,124,152],"relevant":[87],"current":[90],"sample,":[91],"thereby":[92],"improving":[93],"anchoring":[96],"stable":[100],"instance-level":[101],"evidence":[103],"reducing":[105],"influence":[107],"of":[108,121,133,150,184,204],"noisy":[109],"supervision.":[110],"To":[111],"address":[112],"instability":[114,177],"caused":[115],"using":[117],"same":[119],"way":[120],"injecting":[122],"all":[126],"samples,":[127],"despite":[128],"differences":[129],"in":[130,178],"quality":[132],"their":[134],"cues,":[136],"further":[138],"introduce":[139],"conditional":[142],"modulation":[143],"adaptively":[146],"control":[147],"strength":[149],"injection,":[153],"strikes":[155],"balance":[159],"between":[160],"text-side":[161],"priors":[163],"image-side":[165],"instance":[166],"evidence.":[167],"The":[168],"proposed":[169],"effectively":[171],"suppresses":[172],"noise-induced":[174],"disturbances,":[175],"reduce":[176],"updates,":[180],"alleviate":[182],"memorization":[183],"mislabeled":[185],"samples.":[186],"VisPrompt":[187,218],"significantly":[188],"improves":[189],"while":[191],"keeping":[192],"pretrained":[194],"VLM":[195],"backbone":[196],"frozen":[197],"introducing":[199],"only":[200],"small":[202],"amount":[203],"additional":[205],"trainable":[206],"parameters.":[207],"Extensive":[208],"experiments":[209],"synthetic":[211],"real-world":[213],"demonstrate":[216],"that":[217],"generally":[219],"outperforms":[220],"existing":[221],"baselines":[222],"on":[223],"seven":[224],"benchmark":[225],"datasets":[226],"achieves":[228],"stronger":[229],"robustness.":[230],"Our":[231],"code":[232],"publicly":[234],"available":[235],"at":[236],"https://github.com/gezbww/Vis_Prompt.":[237]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-14T00:00:00"}