{"id":"https://openalex.org/W4415537210","doi":"https://doi.org/10.1145/3746027.3754920","title":"Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection","display_name":"Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537210","doi":"https://doi.org/10.1145/3746027.3754920"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754920","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5015011504","display_name":"Yilin Lu","orcid":"https://orcid.org/0009-0000-3266-6155"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yilin Lu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0000-3266-6155","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069323421","display_name":"Jianghang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianghang Lin","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0009-3873-3860","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048814053","display_name":"Linhuang Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linhuang Xie","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0006-6026-5571","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Zhao","orcid":"https://orcid.org/0009-0001-5847-4749"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Zhao","raw_affiliation_strings":["vivo, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0001-5847-4749","affiliations":[{"raw_affiliation_string":"vivo, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102898975","display_name":"Yansong Qu","orcid":"https://orcid.org/0009-0003-4325-6858"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yansong Qu","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0003-4325-6858","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033991031","display_name":"Shengchuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchuan Zhang","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0002-0800-0609","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014628588","display_name":"Liujuan Cao","orcid":"https://orcid.org/0000-0002-7645-9606"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujuan Cao","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0002-7645-9606","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0001-9163-2932","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5015011504"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41947914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11259","last_page":"11268"},"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":0.9991999864578247,"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":0.9991999864578247,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9979000091552734,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9914000034332275,"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/anomaly-detection","display_name":"Anomaly detection","score":0.7922999858856201},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.7717999815940857},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6241000294685364},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5921000242233276},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4311999976634979}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7922999858856201},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.7717999815940857},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6241000294685364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6223999857902527},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5921000242233276},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4932999908924103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47369998693466187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4311999976634979},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754920","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3101101154","display_name":null,"funder_award_id":"U21B2037, U22B2051, U23A20383, U21A20472, 62176222, 62176223, 62176226, 62072386, 62072387, 62072389, 62002305, 62272401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2051224630","https://openalex.org/W2085487226","https://openalex.org/W2163352848","https://openalex.org/W2194775991","https://openalex.org/W2786446225","https://openalex.org/W2948982773","https://openalex.org/W2985068832","https://openalex.org/W3109715690","https://openalex.org/W3166166117","https://openalex.org/W3169651898","https://openalex.org/W3174480022","https://openalex.org/W3178406257","https://openalex.org/W3217427959","https://openalex.org/W4212874935","https://openalex.org/W4214694907","https://openalex.org/W4229858876","https://openalex.org/W4286976841","https://openalex.org/W4312289809","https://openalex.org/W4312772600","https://openalex.org/W4312933868","https://openalex.org/W4386065385","https://openalex.org/W4386065890","https://openalex.org/W4390872231","https://openalex.org/W4413157265"],"related_works":[],"abstract_inverted_index":{"Anomaly":[0,60,129],"inspection":[1],"plays":[2],"a":[3,62,76,91,147,162],"vital":[4],"role":[5],"in":[6,22,194],"industrial":[7],"manufacturing,":[8],"but":[9],"the":[10,17,72,106,118,141,172,176,182],"scarcity":[11],"of":[12,19,75,94,112,122,136,143,175],"anomaly":[13,31,65,137,144,196],"samples":[14],"significantly":[15],"limits":[16],"effectiveness":[18],"existing":[20],"methods":[21],"tasks":[23,201],"such":[24,202],"as":[25,203],"localization":[26,204],"and":[27,49,85,109,120,157,185,199,205],"classification.":[28,206],"While":[29],"several":[30],"synthesis":[32,197],"approaches":[33],"have":[34],"been":[35],"introduced":[36,168],"for":[37],"data":[38],"augmentation,":[39],"they":[40],"often":[41],"struggle":[42],"with":[43],"low":[44],"realism,":[45],"inaccurate":[46],"mask":[47,149],"alignment,":[48],"poor":[50],"generalization.":[51],"To":[52],"overcome":[53],"these":[54],"limitations,":[55],"we":[56],"propose":[57],"Generate":[58],"Aligned":[59],"(GAA),":[61],"region-guided,":[63],"few-shot":[64],"image-mask":[66],"pair":[67],"generation":[68,150],"framework.":[69],"GAA":[70,190],"leverages":[71],"strong":[73],"priors":[74],"pretrained":[77],"latent":[78],"diffusion":[79],"model":[80,105],"to":[81,103,131,169],"generate":[82],"realistic,":[83],"diverse,":[84],"semantically":[86],"aligned":[87],"anomalies":[88,156],"using":[89],"only":[90],"small":[92],"number":[93],"samples.":[95,178],"The":[96],"framework":[97],"first":[98],"employs":[99],"Localized":[100],"Concept":[101],"Decomposition":[102],"jointly":[104],"semantic":[107,134],"features":[108],"spatial":[110],"information":[111],"anomalies,":[113],"enabling":[114],"flexible":[115],"control":[116],"over":[117],"type":[119],"location":[121],"anomalies.":[123],"It":[124],"then":[125],"utilizes":[126],"Adaptive":[127],"Multi-Round":[128],"Clustering":[130],"perform":[132],"fine-grained":[133],"clustering":[135],"concepts,":[138],"thereby":[139],"enhancing":[140],"consistency":[142],"representations.":[145],"Subsequently,":[146],"region-guided":[148],"strategy":[151],"ensures":[152],"precise":[153],"alignment":[154],"between":[155],"their":[158],"corresponding":[159],"masks,":[160],"while":[161],"low-quality":[163],"sample":[164],"filtering":[165],"module":[166],"is":[167],"further":[170],"improve":[171],"overall":[173],"quality":[174,198],"generated":[177],"Extensive":[179],"experiments":[180],"on":[181],"MVTec":[183],"AD":[184],"LOCO":[186],"datasets":[187],"demonstrate":[188],"that":[189],"achieves":[191],"superior":[192],"performance":[193],"both":[195],"downstream":[200]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}