{"id":"https://openalex.org/W7125972416","doi":"https://doi.org/10.1109/smc58881.2025.11343148","title":"Analyzing the Calibration of CLIP Models Under Noisy Data Conditions","display_name":"Analyzing the Calibration of CLIP Models Under Noisy Data Conditions","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125972416","doi":"https://doi.org/10.1109/smc58881.2025.11343148"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5067964451","display_name":"Yuxin Gao","orcid":"https://orcid.org/0009-0007-6160-4536"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxin Gao","raw_affiliation_strings":["Guilin University of Electronic Technology,Laboratory for AIPM, School of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,Laboratory for AIPM, School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055916281","display_name":"Yihang Wu","orcid":"https://orcid.org/0000-0002-8640-8650"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihang Wu","raw_affiliation_strings":["Guilin University of Electronic Technology,Laboratory for AIPM, School of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,Laboratory for AIPM, School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024700033","display_name":"Ahmad Chaddad","orcid":"https://orcid.org/0000-0003-3402-9576"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ahmad Chaddad","raw_affiliation_strings":["Guilin University of Electronic Technology,Laboratory for AIPM, School of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"Guilin University of Electronic Technology,Laboratory for AIPM, School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I5343935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067964451"],"corresponding_institution_ids":["https://openalex.org/I5343935"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8783577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3224","last_page":"3229"},"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":0.7870000004768372,"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":0.7870000004768372,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07760000228881836,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.023099999874830246,"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/calibration","display_name":"Calibration","score":0.8026999831199646},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6642000079154968},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.6276999711990356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4185999929904938},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.362199991941452},{"id":"https://openalex.org/keywords/overconfidence-effect","display_name":"Overconfidence effect","score":0.3084000051021576},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.30489999055862427}],"concepts":[{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.8026999831199646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894999742507935},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6642000079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373000144958496},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.6276999711990356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.362199991941452},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C174576160","wikidata":"https://www.wikidata.org/wiki/Q1183700","display_name":"Deconvolution","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W4214592090","https://openalex.org/W4382457317","https://openalex.org/W4386523254","https://openalex.org/W4387789919","https://openalex.org/W4390190073","https://openalex.org/W4390873546","https://openalex.org/W4390992140","https://openalex.org/W4400767051","https://openalex.org/W4401450512","https://openalex.org/W4402352357","https://openalex.org/W4402727054","https://openalex.org/W4403649873","https://openalex.org/W4403998337","https://openalex.org/W4406612098","https://openalex.org/W4407946271","https://openalex.org/W4410296563","https://openalex.org/W4411336859","https://openalex.org/W4417273915"],"related_works":[],"abstract_inverted_index":{"Contrastive":[0],"Language-Image":[1],"Pretraining":[2],"(CLIP)":[3],"has":[4,28],"emerged":[5],"as":[6],"a":[7,177],"powerful":[8],"paradigm":[9],"for":[10,182],"cross-modal":[11,173],"learning,":[12],"using":[13,54],"image-text":[14],"pairs":[15],"to":[16,40,79,155],"achieve":[17],"remarkable":[18],"zero-shot":[19],"classification":[20],"performance.":[21],"However,":[22,129],"its":[23,163],"calibration":[24,48,81,108,171],"on":[25,127,143,146,157,160],"noisy":[26,183],"data":[27],"been":[29],"less":[30],"explored,":[31],"especially":[32],"in":[33,113,133,172],"out-of-distribution":[34],"settings":[35,115],"where":[36],"overconfidence":[37],"can":[38],"lead":[39],"misclassification.":[41],"In":[42,72],"this":[43],"work,":[44],"we":[45,74,151],"evaluate":[46],"CLIP\u2019s":[47],"ability":[49],"under":[50],"different":[51],"noise":[52,56],"conditions":[53],"10":[55],"types":[57],"from":[58],"the":[59,95,168],"ImageNet-C":[60],"dataset,":[61],"including":[62],"natural":[63],"noise,":[64,66,68],"digital":[65],"weather":[67],"and":[69,86,94,105,175,184],"blur":[70],"noise.":[71],"addition,":[73],"propose":[75],"test-time":[76],"augmentation":[77],"(TTA)":[78],"improve":[80],"by":[82],"increasing":[83],"prediction":[84],"diversity":[85],"reducing":[87],"overconfidence.":[88],"We":[89],"conduct":[90],"~":[91],"600":[92],"simulations,":[93],"experimental":[96],"results":[97,166],"show":[98],"that":[99],"ViT-B/32":[100,132],"achieves":[101],"higher":[102],"accuracy":[103],"(ACC)":[104],"lower":[106],"expected":[107],"error":[109],"(ECE)":[110],"than":[111],"ResNet50":[112,130],"in-distribution":[114],"(e.g.,":[116,137],"94.66%":[117],"ACC":[118],"vs.":[119,124,140],"62.37%":[120],"ACC,":[121],"0.59%":[122],"ECE":[123,126,139,142,154],"1.03%":[125],"brightness).":[128],"outperforms":[131],"out-of-domain":[134],"(OOD)":[135],"situations":[136],"3.14%":[138],"20.93%":[141],"defocus,":[144],"fine-tuned":[145],"glass).":[147],"By":[148],"applying":[149],"TTA,":[150],"reduce":[152],"ViT-B/32\u2019s":[153],"13.07%":[156],"defocus":[158],"(fine-tuned":[159],"glass),":[161],"demonstrating":[162],"effectiveness.":[164],"Our":[165,187],"highlight":[167],"importance":[169],"of":[170],"learning":[174],"provide":[176],"simple":[178],"yet":[179],"effective":[180],"solution":[181],"OOD":[185],"calibration.":[186],"code":[188],"is":[189],"available":[190],"at:":[191],"https://github.com/AIPMLab/CLIPSimulationsGao.":[192]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-29T00:00:00"}