{"id":"https://openalex.org/W7131076986","doi":"https://doi.org/10.1109/iccvw69036.2025.00148","title":"Two-stage Text-Guided Diffusion Models for Disentangled Industrial Defect Generation","display_name":"Two-stage Text-Guided Diffusion Models for Disentangled Industrial Defect Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131076986","doi":"https://doi.org/10.1109/iccvw69036.2025.00148"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085428350","display_name":"Jiaju Wei","orcid":"https://orcid.org/0000-0002-8803-7056"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wei","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126625476","display_name":"Qingfeng Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingfeng Shi","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126640667","display_name":"Fei Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Shen","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126656928","display_name":"Zhengtao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtao Zhang","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65308826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1387","last_page":"1395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.16140000522136688,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.16140000522136688,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.06769999861717224,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.03840000182390213,"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/adapter","display_name":"Adapter (computing)","score":0.7379000186920166},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5845000147819519},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4772000014781952},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.40720000863075256},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3546000123023987},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.33399999141693115}],"concepts":[{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7379000186920166},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5845000147819519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5569999814033508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4934000074863434},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4772000014781952},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.32600000500679016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29490000009536743},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2741999924182892},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.44688114523887634,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2410815021","display_name":null,"funder_award_id":"L243018","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2948982773","https://openalex.org/W2954996726","https://openalex.org/W2962785568","https://openalex.org/W3119769313","https://openalex.org/W3164289800","https://openalex.org/W3213997984","https://openalex.org/W4301206121","https://openalex.org/W4312933868","https://openalex.org/W4313404331","https://openalex.org/W4320401871","https://openalex.org/W4320525814","https://openalex.org/W4380244347","https://openalex.org/W4382240612","https://openalex.org/W4385804900","https://openalex.org/W4390873054","https://openalex.org/W4390874575","https://openalex.org/W4393148714","https://openalex.org/W4393159787"],"related_works":[],"abstract_inverted_index":{"Defect":[0],"image":[1],"generation":[2,16],"is":[3,99,150],"crucial":[4],"to":[5,19,53,75,101,108,137,152,184,189,207],"address":[6],"the":[7,55,72,85,96,103,109,113,117,128,139,142,146,154,159,162],"data":[8],"scarcity":[9],"problem":[10],"in":[11,31,191],"industrial":[12,41],"inspection.":[13],"However,":[14],"current":[15],"methods":[17],"struggle":[18],"produce":[20],"high-quality":[21,213],"defect":[22,67,97,120,177,203,215],"images":[23,83],"with":[24,116,127,179],"limited":[25,180],"training":[26,181],"samples.":[27,164],"The":[28],"reason":[29],"lies":[30],"that":[32,168],"they":[33],"focus":[34],"solely":[35],"on":[36],"imaging":[37],"characteristics":[38],"rather":[39],"than":[40],"manufacturing.":[42],"To":[43],"tackle":[44],"this":[45,47],"issue,":[46],"paper":[48],"proposes":[49],"a":[50],"two-stage":[51],"method":[52,170],"simulate":[54],"actual":[56],"manufacturing":[57],"process":[58],"of":[59,87,119,141,161,187,194],"defective":[60],"products":[61,65],"by":[62],"disentangling":[63],"normal":[64,73,82,110],"and":[66,80,91,123,134,175],"operations.":[68],"Firstly,":[69],"we":[70],"design":[71],"adapter":[74,98,204],"fine-tune":[76],"pre-trained":[77],"diffusion":[78],"models":[79],"generate":[81,172],"under":[84],"guidance":[86,118],"product-related":[88],"text":[89],"prompts":[90,122],"global":[92],"uniform":[93],"masks.":[94],"Secondly,":[95],"proposed":[100,129],"learn":[102],"product-agnostic":[104],"damage":[105],"operations":[106],"applied":[107],"features":[111],"from":[112],"first":[114],"stage":[115],"name":[121],"binary":[124],"masks,":[125],"combined":[126],"local":[130],"structural":[131],"consistency":[132],"loss":[133,136],"contrastive":[135],"improve":[138],"quality":[140,160],"generated":[143,163],"defects.":[144],"Subsequently,":[145],"Segment":[147],"Anything":[148],"Model":[149],"employed":[151],"refine":[153],"mask":[155],"annotations,":[156],"further":[157],"enhancing":[158],"Experimental":[165],"results":[166],"demonstrate":[167],"our":[169,202],"can":[171],"high-quality,":[173],"diverse,":[174],"annotated":[176],"samples":[178],"samples,":[182],"leading":[183],"an":[185],"improvement":[186],"up":[188],"7%":[190],"average":[192],"precision":[193],"segmentation":[195],"performance,":[196],"outperforming":[197],"existing":[198],"state-of-the-art":[199],"methods.":[200],"Moreover,":[201],"enables":[205],"defects":[206],"transfer":[208],"across":[209],"different":[210],"products,":[211],"achieving":[212],"zero-shot":[214],"generation.":[216]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-24T00:00:00"}