{"id":"https://openalex.org/W4402502610","doi":"https://doi.org/10.1145/3664647.3680664","title":"CLIPCleaner: Cleaning Noisy Labels with CLIP","display_name":"CLIPCleaner: Cleaning Noisy Labels with CLIP","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4402502610","doi":"https://doi.org/10.1145/3664647.3680664"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680664","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.10012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100352678","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0001-9199-559X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chen Feng","raw_affiliation_strings":["Queen Mary University London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-9199-559X","affiliations":[{"raw_affiliation_string":"Queen Mary University London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024224610","display_name":"Georgios Tzimiropoulos","orcid":"https://orcid.org/0000-0002-1803-5338"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgios Tzimiropoulos","raw_affiliation_strings":["Queen Mary University London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-1803-5338","affiliations":[{"raw_affiliation_string":"Queen Mary University London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031205865","display_name":"Ioannis Patras","orcid":"https://orcid.org/0000-0003-3913-4738"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ioannis Patras","raw_affiliation_strings":["Queen Mary, University of London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-3913-4738","affiliations":[{"raw_affiliation_string":"Queen Mary, University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7441,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91554409,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"876","last_page":"885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998999834060669,"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":0.9998999834060669,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9901999831199646,"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":0.9804999828338623,"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/computer-science","display_name":"Computer science","score":0.833146333694458},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6858952045440674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6602192521095276},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.643700122833252},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6357448697090149},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5490527153015137},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5283380746841431},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5127618908882141},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3673563003540039},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3426065742969513},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1935952603816986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833146333694458},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6858952045440674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6602192521095276},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.643700122833252},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6357448697090149},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5490527153015137},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5283380746841431},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5127618908882141},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3673563003540039},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3426065742969513},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1935952603816986},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3664647.3680664","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.10012","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.10012","pdf_url":"https://arxiv.org/pdf/2408.10012","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":null,"raw_type":"text"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10199672","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10199672/","pdf_url":"https://discovery.ucl.ac.uk/10199672/1/ACMMM2024_CLIPCleaner_camera_ready.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In:  Proceedings of the 32nd ACM International Conference on Multimedia.  (pp. pp. 876-885).  ACM (2024)","raw_type":"Proceedings paper"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/98922","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/98922","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/98922/2/ACMMM2024_CLIPCleaner_camera_ready.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.10012","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.10012","pdf_url":"https://arxiv.org/pdf/2408.10012","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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402502610.pdf","grobid_xml":"https://content.openalex.org/works/W4402502610.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2963697299","https://openalex.org/W2964292098","https://openalex.org/W2967052791","https://openalex.org/W2981873476","https://openalex.org/W2999905431","https://openalex.org/W3035524453","https://openalex.org/W3110483780","https://openalex.org/W3168479843","https://openalex.org/W3171635822","https://openalex.org/W3175157109","https://openalex.org/W3175272368","https://openalex.org/W3175562011","https://openalex.org/W3198377975","https://openalex.org/W3202345803","https://openalex.org/W4242177601","https://openalex.org/W4310813115","https://openalex.org/W4312464225","https://openalex.org/W4312601326","https://openalex.org/W4313014573","https://openalex.org/W4313135270","https://openalex.org/W4319299742","https://openalex.org/W4319300183","https://openalex.org/W4386075521","https://openalex.org/W4386076172","https://openalex.org/W4386076217","https://openalex.org/W4394593004","https://openalex.org/W4400524968","https://openalex.org/W4402703064","https://openalex.org/W4402716216","https://openalex.org/W6801615203"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Learning":[0,12,228],"with":[1,185,229],"Noisy":[2,230],"labels":[3],"(LNL)":[4],"poses":[5],"a":[6,96,102,109,190,214],"significant":[7],"challenge":[8,71],"for":[9,26,107,112,169,220],"the":[10,16,28,43,52,61,66,76,120,123,129,134,140,146,150,165,204,211,225,237],"Machine":[11],"community.":[13],"Some":[14],"of":[15,75,139,167,206,227],"most":[17],"widely":[18],"used":[19,219],"approaches":[20],"that":[21,82,99,122,133,152,180,194],"select":[22],"as":[23],"clean":[24,115],"samples":[25],"which":[27],"model":[29,106,131,216],"itself":[30],"(the":[31],"in-training":[32,53,130],"model)":[33],"has":[34,119,217],"high":[35],"confidence,":[36],"e.g.,":[37],"'small":[38],"loss',":[39],"can":[40],"suffer":[41],"from":[42,128],"so":[44],"called":[45],"'self-confirmation'":[46],"bias.":[47],"This":[48,89,118],"bias":[49],"arises":[50,72],"because":[51,73],"model,":[54],"is":[55,79,126,137,154,210],"at":[56],"least":[57],"partially":[58],"trained":[59],"on":[60,200],"noisy":[62],"labels.":[63],"Furthermore,":[64],"in":[65,236],"classification":[67],"case,":[68],"an":[69],"additional":[70],"some":[74],"label":[77],"noise":[78],"between":[80,145],"classes":[81,147],"are":[83],"visually":[84],"very":[85],"similar":[86],"('hard":[87],"noise').":[88],"paper":[90],"addresses":[91],"these":[92],"challenges":[93],"by":[94],"proposing":[95],"method":[97],"(CLIPCleaner)":[98],"leverages":[100],"CLIP,":[101],"powerful":[103],"Vision-Language":[104],"(VL)":[105],"constructing":[108],"zero-shot":[110],"classifier":[111],"efficient,":[113],"offline,":[114],"sample":[116,124,135,183,221],"selection.":[117],"advantage":[121],"selection":[125,136,184,222],"decoupled":[127],"and":[132,142,160],"aware":[138],"semantic":[141],"visual":[143],"similarities":[144],"due":[148],"to":[149,163,172,177,223],"way":[151],"CLIP":[153,168],"trained.":[155],"We":[156],"provide":[157],"theoretical":[158],"justifications":[159],"empirical":[161],"evidence":[162],"demonstrate":[164],"advantages":[166],"LNL":[170],"compared":[171],"conventional":[173],"pre-trained":[174],"models.":[175],"Compared":[176],"current":[178],"methods":[179],"combine":[181],"iterative":[182],"various":[186],"techniques,":[187],"CLIPCleaner":[188],"offers":[189],"simple,":[191],"single-step":[192],"approach":[193],"achieves":[195],"competitive":[196],"or":[197],"superior":[198],"performance":[199],"benchmark":[201],"datasets.":[202],"To":[203],"best":[205],"our":[207],"knowledge,":[208],"this":[209],"first":[212],"time":[213],"VL":[215],"been":[218],"address":[224],"problem":[226],"Labels":[231],"(LNL),":[232],"highlighting":[233],"their":[234],"potential":[235],"domain.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}