{"id":"https://openalex.org/W4416250936","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227884","title":"Robust-CLIP: End-to-End Fine-Tuning of Vision-Language Models under Noisy Labels","display_name":"Robust-CLIP: End-to-End Fine-Tuning of Vision-Language Models under Noisy Labels","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250936","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227884"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100783381","display_name":"Guan-Yu Chen","orcid":"https://orcid.org/0009-0002-3014-178X"},"institutions":[{"id":"https://openalex.org/I4210165407","display_name":"Intelligent Decision Systems (Spain)","ror":"https://ror.org/05xp52m23","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210165407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Guanyu Chen","raw_affiliation_strings":["Intelligent Game and Decision Lab(IGDL),Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab(IGDL),Beijing,China","institution_ids":["https://openalex.org/I4210165407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101477549","display_name":"Ruihao Li","orcid":"https://orcid.org/0000-0002-7092-2401"},"institutions":[{"id":"https://openalex.org/I4210165407","display_name":"Intelligent Decision Systems (Spain)","ror":"https://ror.org/05xp52m23","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210165407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ruihao Li","raw_affiliation_strings":["Intelligent Game and Decision Lab(IGDL),Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab(IGDL),Beijing,China","institution_ids":["https://openalex.org/I4210165407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038147807","display_name":"Defu Liu","orcid":"https://orcid.org/0000-0001-9000-7262"},"institutions":[{"id":"https://openalex.org/I4210165407","display_name":"Intelligent Decision Systems (Spain)","ror":"https://ror.org/05xp52m23","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210165407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Defu Liu","raw_affiliation_strings":["Intelligent Game and Decision Lab(IGDL),Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab(IGDL),Beijing,China","institution_ids":["https://openalex.org/I4210165407"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668111","display_name":"Wei Yi","orcid":"https://orcid.org/0000-0002-8880-6038"},"institutions":[{"id":"https://openalex.org/I4210165407","display_name":"Intelligent Decision Systems (Spain)","ror":"https://ror.org/05xp52m23","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210165407"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Wei Yi","raw_affiliation_strings":["Intelligent Game and Decision Lab(IGDL),Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab(IGDL),Beijing,China","institution_ids":["https://openalex.org/I4210165407"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.1654015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.8640000224113464,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.8640000224113464,"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":0.01489999983459711,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.012900000438094139,"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/noise","display_name":"Noise (video)","score":0.6101999878883362},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5771999955177307},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5595999956130981},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.49880000948905945},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4715999960899353},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4537000060081482},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.448199987411499}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6388000249862671},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6101999878883362},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5771999955177307},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5595999956130981},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3449000120162964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W1921293667","https://openalex.org/W2403681572","https://openalex.org/W2962762068","https://openalex.org/W2963509340","https://openalex.org/W2964273174","https://openalex.org/W2964292098","https://openalex.org/W2967052791","https://openalex.org/W2978625989","https://openalex.org/W3042609801","https://openalex.org/W3121661476","https://openalex.org/W3168479843","https://openalex.org/W3171635822","https://openalex.org/W3186514747","https://openalex.org/W3198377975","https://openalex.org/W3204785235","https://openalex.org/W4283838088","https://openalex.org/W4285606530","https://openalex.org/W4286611322","https://openalex.org/W4287947470","https://openalex.org/W4312601326","https://openalex.org/W4312651322","https://openalex.org/W4312818263","https://openalex.org/W4313135270","https://openalex.org/W4313175608","https://openalex.org/W4319300183","https://openalex.org/W4386071687","https://openalex.org/W4386075521","https://openalex.org/W4386790226","https://openalex.org/W4390871786","https://openalex.org/W4402502610","https://openalex.org/W4402727000","https://openalex.org/W4402727610","https://openalex.org/W4402783842"],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Pre-Trained":[1],"Models,":[2],"like":[3],"CLIP,":[4],"have":[5],"shown":[6],"strong":[7],"potential":[8],"in":[9,167],"connecting":[10],"images":[11],"and":[12,44,78,104,114,134,144,171],"text":[13,103],"across":[14],"different":[15],"tasks.":[16],"However,":[17],"most":[18],"fine-tuning":[19],"methods":[20],"overlook":[21],"the":[22,35,102,125,156,174],"fact":[23],"that":[24,58,148],"real-world":[25,135],"datasets":[26],"often":[27],"contain":[28],"noisy":[29,38,136,184],"labels,":[30],"especially":[31],"when":[32,181],"collected":[33],"from":[34],"web.":[36],"These":[37],"labels":[39,110],"can":[40],"reduce":[41],"model":[42],"performance":[43],"make":[45],"training":[46,90],"less":[47],"stable.":[48],"To":[49],"address":[50],"this":[51],"issue,":[52],"we":[53,93],"introduce":[54],"Robust-CLIP,":[55],"a":[56,69,79,85,96,112],"framework":[57],"combines":[59],"clean":[60,126],"sample":[61],"selection":[62],"with":[63,121],"semi-supervised":[64],"fine-tuning.":[65],"Our":[66,161],"approach":[67],"leverages":[68],"joint":[70],"prompt":[71],"pre-selection":[72],"module,":[73],"which":[74],"utilizes":[75],"multiple":[76],"prompts":[77],"dynamic":[80],"weighting":[81],"mechanism":[82],"to":[83,124],"isolate":[84],"more":[86],"reliable":[87],"subset":[88],"of":[89,159,169,177],"data.":[91],"Additionally,":[92],"propose":[94],"SemiLoRA,":[95],"parameter-efficient":[97],"method":[98,108,162],"for":[99],"updating":[100],"both":[101,132],"image":[105],"encoders.":[106],"This":[107],"refines":[109],"through":[111],"relabeling":[113],"MixMatch":[115],"process,":[116],"while":[117,154],"dynamically":[118],"promoting":[119],"samples":[120],"high":[122],"confidence":[123],"set.":[127],"Extensive":[128],"experiments":[129],"conducted":[130],"on":[131],"synthetic":[133],"datasets,":[137],"including":[138],"CIFAR-10/100,":[139],"Clothing1M,":[140],"WebVision,":[141],"Food-101N,":[142],"ANIMAL-10N,":[143],"Red":[145],"Mini-Imagenet,":[146],"demonstrate":[147],"Robust-CLIP":[149],"effectively":[150],"mitigates":[151],"label":[152,185],"noise":[153],"preserving":[155],"cross-modal":[157],"strengths":[158],"CLIP.":[160],"consistently":[163],"outperforms":[164],"previous":[165],"approaches":[166],"terms":[168],"accuracy":[170],"robustness,":[172],"highlighting":[173],"critical":[175],"importance":[176],"leveraging":[178],"vision-language":[179],"alignment":[180],"learning":[182],"under":[183],"conditions.":[186]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}