{"id":"https://openalex.org/W7164865463","doi":"https://doi.org/10.1145/3805622.3810587","title":"Adaptive Knowledge-Language Alignment for Industrial Anomaly Detection and Segmentation","display_name":"Adaptive Knowledge-Language Alignment for Industrial Anomaly Detection and Segmentation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164865463","doi":"https://doi.org/10.1145/3805622.3810587"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810587","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810587","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017146112","display_name":"Shih-Chih Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Shih-Chih Lin","raw_affiliation_strings":["International Intercollegiate Ph.D. Program, National Tsing Hau University, Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0009-0001-8762-5497","affiliations":[{"raw_affiliation_string":"International Intercollegiate Ph.D. Program, National Tsing Hau University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5017146112"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.95139731,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.5307999849319458,"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":0.5307999849319458,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.14159999787807465,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09120000153779984,"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/anomaly-detection","display_name":"Anomaly detection","score":0.7935000061988831},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6254000067710876},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5978999733924866},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5547000169754028},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4754999876022339},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.4666999876499176},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.453000009059906},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3977000117301941},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.3919000029563904},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.38940000534057617}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7935000061988831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7296000123023987},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6254000067710876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6097999811172485},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5978999733924866},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5547000169754028},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3919000029563904},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37279999256134033},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34940001368522644},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C110893760","wikidata":"https://www.wikidata.org/wiki/Q3115590","display_name":"Named graph","level":5,"score":0.26570001244544983},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810587","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810587","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5524964928627014,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2047643928","https://openalex.org/W3209793239","https://openalex.org/W4312605624","https://openalex.org/W4386065385","https://openalex.org/W4402702916","https://openalex.org/W4402716375","https://openalex.org/W4413278288","https://openalex.org/W7131064309","https://openalex.org/W7133224946"],"related_works":[],"abstract_inverted_index":{"Industrial":[0],"anomaly":[1,136],"detection":[2,137],"and":[3,52,75,87,102,145,159,166,184],"segmentation":[4],"require":[5],"models":[6,24],"that":[7,177],"generalize":[8],"across":[9],"unseen":[10,148],"object":[11],"categories":[12],"while":[13,104],"remaining":[14],"highly":[15],"sensitive":[16],"to":[17,35],"subtle,":[18],"localized":[19],"defects.":[20],"While":[21],"CLIP-based":[22],"vision-language":[23],"offer":[25],"powerful":[26],"zero-shot":[27,135],"priors,":[28],"cross-dataset":[29,191],"deployment":[30,63],"remains":[31],"notoriously":[32],"unstable":[33,53],"due":[34],"three":[36],"critical":[37],"failure":[38],"modes:":[39],"semantic":[40,97,182],"ambiguity":[41],"from":[42],"text-anchor":[43,100],"collapse,":[44],"noisy":[45],"dense":[46],"visual":[47,113],"responses":[48],"on":[49,141,147],"normal":[50],"backgrounds,":[51],"image-level":[54,167],"scoring":[55],"dominated":[56],"by":[57,121],"outlier":[58],"patches.":[59],"To":[60],"overcome":[61],"these":[62],"bottlenecks,":[64],"we":[65,117,139],"propose":[66],"AKLAR":[67,80,161],"(Adaptive":[68],"Knowledge\u2013Language":[69],"Alignment":[70],"for":[71,189],"Recognition),":[72],"a":[73,89,126,142],"lightweight":[74],"principled":[76],"two-stage":[77],"adaptation":[78],"framework.":[79],"keeps":[81],"the":[82,178],"CLIP":[83],"foundation":[84],"strictly":[85],"frozen":[86],"introduces":[88],"systematic":[90],"alignment":[91],"strategy:":[92],"Stage":[93,105],"1":[94],"explicitly":[95],"establishes":[96],"controllability":[98],"through":[99],"separation":[101],"preservation,":[103],"2":[106],"ensures":[107],"spatial":[108],"fidelity":[109],"via":[110],"EMA-stabilized":[111],"multi-scale":[112],"adapters.":[114],"During":[115],"inference,":[116],"maintain":[118],"evaluation":[119],"integrity":[120],"replacing":[122],"noise-sensitive":[123],"max-pooling":[124],"with":[125],"robust":[127,190],"top-k":[128],"dense-to-global":[129],"evidence":[130,185],"aggregation":[131],"mechanism.":[132],"Following":[133],"standard":[134],"protocols,":[138],"train":[140],"source":[143],"benchmark":[144],"evaluate":[146],"industrial":[149,192],"targets.":[150],"Across":[151],"five":[152],"diverse":[153],"benchmarks":[154],"(MVTec-AD,":[155],"VisA,":[156],"BTAD,":[157],"DTD,":[158],"DAGM),":[160],"consistently":[162],"improves":[163],"region-level":[164],"localization":[165],"retrieval":[168],"metrics":[169],"without":[170],"any":[171],"target-domain":[172],"fine-tuning.":[173],"These":[174],"results":[175],"demonstrate":[176],"deliberate":[179],"coordination":[180],"of":[181],"stabilization":[183],"calibration":[186],"is":[187,196],"essential":[188],"inspection.":[193],"The":[194],"code":[195],"available":[197],"at":[198],"https://github.com/leolin65/AKLAR.git.":[199]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}