{"id":"https://openalex.org/W4411142698","doi":"https://doi.org/10.1007/s00521-025-11367-3","title":"Multi-model anomaly detection for industrial inspection with dynamic loss weighting and soft-hard features loss","display_name":"Multi-model anomaly detection for industrial inspection with dynamic loss weighting and soft-hard features loss","publication_year":2025,"publication_date":"2025-06-09","ids":{"openalex":"https://openalex.org/W4411142698","doi":"https://doi.org/10.1007/s00521-025-11367-3"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-025-11367-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11367-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11367-3.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11367-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039694103","display_name":"Willy Fitra Hendria","orcid":"https://orcid.org/0000-0002-6209-3981"},"institutions":[{"id":"https://openalex.org/I196733613","display_name":"Korea Gas Corporation (South Korea)","ror":"https://ror.org/0058p8h34","country_code":"KR","type":"company","lineage":["https://openalex.org/I196733613"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Willy Fitra Hendria","raw_affiliation_strings":["Dagyeom, 801, 146, Gasan digital 1-ro, Geumcheon-gu, Seoul, 08507, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dagyeom, 801, 146, Gasan digital 1-ro, Geumcheon-gu, Seoul, 08507, Republic of Korea","institution_ids":["https://openalex.org/I196733613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104296212","display_name":"Hanbi Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I196733613","display_name":"Korea Gas Corporation (South Korea)","ror":"https://ror.org/0058p8h34","country_code":"KR","type":"company","lineage":["https://openalex.org/I196733613"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanbi Kim","raw_affiliation_strings":["Dagyeom, 801, 146, Gasan digital 1-ro, Geumcheon-gu, Seoul, 08507, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dagyeom, 801, 146, Gasan digital 1-ro, Geumcheon-gu, Seoul, 08507, Republic of Korea","institution_ids":["https://openalex.org/I196733613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111981884","display_name":"Daeho Seo","orcid":null},"institutions":[{"id":"https://openalex.org/I196733613","display_name":"Korea Gas Corporation (South Korea)","ror":"https://ror.org/0058p8h34","country_code":"KR","type":"company","lineage":["https://openalex.org/I196733613"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daeho Seo","raw_affiliation_strings":["Dagyeom, 801, 146, Gasan digital 1-ro, Geumcheon-gu, Seoul, 08507, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dagyeom, 801, 146, Gasan digital 1-ro, Geumcheon-gu, Seoul, 08507, Republic of Korea","institution_ids":["https://openalex.org/I196733613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039694103"],"corresponding_institution_ids":["https://openalex.org/I196733613"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":8.6423,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97277029,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"37","issue":"21","first_page":"17031","last_page":"17054"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","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/T11512","display_name":"Anomaly Detection Techniques and Applications","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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9958000183105469,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9825000166893005,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/weighting","display_name":"Weighting","score":0.6686108708381653},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.6205371618270874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6105359792709351},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5466828346252441},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5406839847564697},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38663387298583984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33632874488830566},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2569057047367096},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1368456482887268},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08869296312332153}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6686108708381653},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.6205371618270874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6105359792709351},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5466828346252441},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5406839847564697},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38663387298583984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33632874488830566},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2569057047367096},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1368456482887268},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08869296312332153},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-025-11367-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11367-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11367-3.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-025-11367-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11367-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11367-3.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411142698.pdf","grobid_xml":"https://content.openalex.org/works/W4411142698.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W2065202763","https://openalex.org/W2066219179","https://openalex.org/W2108598243","https://openalex.org/W2134490011","https://openalex.org/W2143559571","https://openalex.org/W2144182447","https://openalex.org/W2194775991","https://openalex.org/W2289015916","https://openalex.org/W2475668412","https://openalex.org/W2599354622","https://openalex.org/W2796762894","https://openalex.org/W2914543430","https://openalex.org/W2914570111","https://openalex.org/W2948982773","https://openalex.org/W2963045681","https://openalex.org/W2964137095","https://openalex.org/W2982324952","https://openalex.org/W2990346675","https://openalex.org/W3034314048","https://openalex.org/W3040266635","https://openalex.org/W3100850306","https://openalex.org/W3118600296","https://openalex.org/W3127508419","https://openalex.org/W3135550350","https://openalex.org/W3147184966","https://openalex.org/W3156089232","https://openalex.org/W3168984673","https://openalex.org/W3169077988","https://openalex.org/W3169651898","https://openalex.org/W4212874935","https://openalex.org/W4310465416","https://openalex.org/W4312605624","https://openalex.org/W4312772600","https://openalex.org/W4319299981","https://openalex.org/W4323240504","https://openalex.org/W4386065775","https://openalex.org/W4394625793","https://openalex.org/W4411244487","https://openalex.org/W6600628372","https://openalex.org/W6603527449"],"related_works":["https://openalex.org/W2806741695","https://openalex.org/W4290647774","https://openalex.org/W3189286258","https://openalex.org/W3207797160","https://openalex.org/W3210364259","https://openalex.org/W4300558037","https://openalex.org/W2667207928","https://openalex.org/W2912112202","https://openalex.org/W4377864969","https://openalex.org/W3120251014"],"abstract_inverted_index":{"Anomaly":[0],"detection":[1,118,126,190],"in":[2,83],"manufacturing":[3],"remains":[4],"a":[5],"significant":[6],"challenge,":[7],"particularly":[8],"due":[9],"to":[10,46,57,77,120,155,165,173,178,207],"the":[11,18,26,65,111,125,139,146,159,169,183,195,199],"unique":[12],"characteristics":[13],"of":[14,20,28,67,127],"industrial":[15,48],"data":[16,49],"and":[17,141,163,211],"scarcity":[19],"abnormal":[21],"samples.":[22],"This":[23,51],"study":[24,52],"investigates":[25],"effectiveness":[27],"unsupervised":[29],"learning":[30],"approaches,":[31],"leveraging":[32],"multi-model":[33,59,209],"frameworks":[34],"that":[35,92,145],"combine":[36],"pre-trained":[37],"models":[38,43],"on":[39,86,138,158,168],"large-scale":[40],"datasets":[41,143],"with":[42,74,100,107,153],"specifically":[44],"trained":[45],"capture":[47],"features.":[50],"proposes":[53],"two":[54],"key":[55],"methodologies":[56],"maximize":[58],"efficiency.":[60],"Dynamic":[61],"loss":[62],"weighting":[63],"optimizes":[64],"contribution":[66],"each":[68],"model":[69],"during":[70],"training,":[71],"enabling":[72,204],"networks":[73],"diverse":[75,208],"expertise":[76],"synergize":[78],"effectively.":[79],"Soft-hard":[80],"feature":[81],"loss,":[82],"particular,":[84],"focuses":[85],"precisely":[87],"capturing":[88],"subtle":[89],"anomaly":[90,117,133,189],"regions":[91],"traditional":[93],"methods":[94],"might":[95],"miss.":[96],"By":[97],"emphasizing":[98],"features":[99],"high-error":[101],"values":[102],"while":[103],"appropriately":[104],"utilizing":[105],"those":[106],"lower":[108],"error":[109],"values,":[110],"proposed":[112,147,184,196],"approach":[113],"enables":[114,186],"more":[115,187],"detailed":[116],"compared":[119,172],"existing":[121],"methods,":[122],"allowing":[123],"for":[124,201],"even":[128],"minor":[129],"defects":[130],"through":[131],"refined":[132],"region":[134],"analysis.":[135],"Quantitative":[136],"results":[137],"MVTec":[140,160],"VisA":[142,170],"demonstrate":[144],"method":[148,185,197],"achieves":[149],"remarkable":[150],"performance":[151],"improvements,":[152],"up":[154,164],"+0.6%":[156],"(AU-PRO)":[157],"AD":[161],"dataset":[162,171],"+0.4%":[166],"(AU-ROC)":[167],"baseline":[174],"methods.":[175],"In":[176],"addition":[177],"its":[179,205],"superior":[180],"quantitative":[181],"performance,":[182],"precise":[188],"than":[191],"conventional":[192],"approaches.":[193],"Furthermore,":[194],"eliminates":[198],"need":[200],"experimental":[202],"tuning,":[203],"application":[206],"approaches":[210],"ensuring":[212],"adaptability":[213],"across":[214],"various":[215],"datasets.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}