{"id":"https://openalex.org/W4410058192","doi":"https://doi.org/10.32604/cmc.2025.064489","title":"An Optimized Unsupervised Defect Detection Approach via Federated Learning and Adaptive Embeddings Knowledge Distillation","display_name":"An Optimized Unsupervised Defect Detection Approach via Federated Learning and Adaptive Embeddings Knowledge Distillation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410058192","doi":"https://doi.org/10.32604/cmc.2025.064489"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.064489","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064489","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.32604/cmc.2025.064489","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100611135","display_name":"Jinhai Wang","orcid":"https://orcid.org/0000-0002-8827-7957"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jinhai Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083628183","display_name":"Junwei Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junwei Xue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385569","display_name":"Hongyan Zhang","orcid":"https://orcid.org/0000-0001-6424-3261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyan Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101904498","display_name":"Hui Xiao","orcid":"https://orcid.org/0000-0003-2374-4021"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039489395","display_name":"Huiling Wei","orcid":"https://orcid.org/0000-0001-5854-6100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huiling Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050848765","display_name":"Mingyou Chen","orcid":"https://orcid.org/0000-0003-0399-4453"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyou Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103392323","display_name":"Jiang Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang Liao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060130626","display_name":"Lufeng Luo","orcid":"https://orcid.org/0000-0003-4106-1558"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lufeng Luo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100611135"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3199,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81004298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"84","issue":"1","first_page":"1839","last_page":"1861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.9210000038146973,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6769388318061829},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6178610324859619},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5930835008621216},{"id":"https://openalex.org/keywords/adaptive-learning","display_name":"Adaptive learning","score":0.5079851746559143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5017304420471191},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.450973242521286},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.1675167679786682},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.16734248399734497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769388318061829},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6178610324859619},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5930835008621216},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.5079851746559143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5017304420471191},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.450973242521286},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.1675167679786682},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.16734248399734497}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32604/cmc.2025.064489","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064489","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.064489","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.064489","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2888407265","https://openalex.org/W2914570111","https://openalex.org/W3093331990","https://openalex.org/W4283756813","https://openalex.org/W4313526338","https://openalex.org/W4313830754","https://openalex.org/W4386767075","https://openalex.org/W4387037473","https://openalex.org/W4395056630","https://openalex.org/W4400244262","https://openalex.org/W4402568614","https://openalex.org/W4403446611","https://openalex.org/W4406064074","https://openalex.org/W4406265389","https://openalex.org/W4406277793"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Defect":[0],"detection":[1,19,55],"based":[2],"on":[3],"computer":[4],"vision":[5],"is":[6,118,136],"a":[7,80,92,112],"critical":[8],"component":[9],"in":[10,24,42,229],"ensuring":[11],"the":[12,28,39,100,125,132,144,192,197,223],"quality":[13],"of":[14,30,35],"industrial":[15,103],"products.":[16],"However,":[17],"existing":[18],"methods":[20,207],"encounter":[21],"several":[22],"challenges":[23],"practical":[25],"applications,":[26],"including":[27],"scarcity":[29],"labeled":[31],"samples,":[32],"limited":[33],"adaptability":[34],"pre-trained":[36,101,210],"models,":[37,131],"and":[38,90,128,157],"data":[40,163],"heterogeneity":[41],"distributed":[43],"environments.":[44],"To":[45],"address":[46],"these":[47],"issues,":[48],"this":[49,73],"research":[50],"proposes":[51,75],"an":[52,178],"unsupervised":[53],"defect":[54,96],"method,":[56],"FLAME":[57],"(Federated":[58],"Learning":[59],"with":[60],"Adaptive":[61],"Multi-Model":[62],"Embeddings).":[63],"The":[64,147],"method":[65],"comprises":[66],"three":[67],"stages:":[68],"(1)":[69],"Feature":[70],"learning":[71,214],"stage:":[72,111,169],"work":[74],"FADE":[76,190],"(Feature-Adaptive":[77],"Domain-Specific":[78],"Embeddings),":[79],"framework":[81],"employs":[82],"Gaussian":[83],"noise":[84],"injection":[85],"to":[86,138,154,176,206],"simulate":[87],"defective":[88],"patterns":[89],"implements":[91],"feature":[93,114,141,218],"discriminator":[94],"for":[95],"detection,":[97],"thereby":[98],"enhancing":[99],"model\u2019s":[102],"imagery":[104],"representation":[105],"capabilities.":[106],"(2)":[107],"Knowledge":[108],"distillation":[109,116,220],"co-training":[110],"multi-model":[113,217],"knowledge":[115,122,184,219],"mechanism":[117,221],"introduced.":[119],"Through":[120],"feature-level":[121],"transfer":[123],"between":[124],"global":[126,145,180],"model":[127,135],"historical":[129],"local":[130,134,150,155],"current":[133],"guided":[137],"learn":[139],"better":[140],"representations":[142],"from":[143,152],"model.":[146],"approach":[148],"prevents":[149],"models":[151],"converging":[153],"optima":[156],"mitigates":[158],"performance":[159],"degradation":[160],"caused":[161],"by":[162,203,227],"heterogeneity.":[164],"(3)":[165],"Model":[166],"parameter":[167],"aggregation":[168,175],"participating":[170],"clients":[171],"utilize":[172],"weighted":[173],"averaging":[174],"synthesize":[177],"updated":[179],"model,":[181],"facilitating":[182],"efficient":[183],"consolidation.":[185],"Experimental":[186],"results":[187],"demonstrate":[188],"that":[189],"improves":[191],"average":[193,230],"image-level":[194,231],"Area":[195],"under":[196],"Receiver":[198],"Operating":[199],"Characteristic":[200],"Curve":[201],"(AUROC)":[202],"7.34%":[204],"compared":[205],"directly":[208],"utilizing":[209],"models.":[211],"In":[212],"federated":[213],"environments,":[215],"FLAME\u2019s":[216],"outperforms":[222],"classic":[224],"FedAvg":[225],"algorithm":[226],"2.34%":[228],"AUROC,":[232],"while":[233],"exhibiting":[234],"superior":[235],"convergence":[236],"properties.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}