{"id":"https://openalex.org/W4408611000","doi":"https://doi.org/10.1109/icaiic64266.2025.10920808","title":"DHR-CLIP: Dynamic High-Resolution Object-Agnostic Prompt Learning for Zero-shot Anomaly Segmentation","display_name":"DHR-CLIP: Dynamic High-Resolution Object-Agnostic Prompt Learning for Zero-shot Anomaly Segmentation","publication_year":2025,"publication_date":"2025-02-18","ids":{"openalex":"https://openalex.org/W4408611000","doi":"https://doi.org/10.1109/icaiic64266.2025.10920808"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic64266.2025.10920808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic64266.2025.10920808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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":null,"display_name":"Jiyul Ham","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiyul Ham","raw_affiliation_strings":["Korea University,Department of Industrial and Management Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Industrial and Management Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021164528","display_name":"Jun\u2010Geol Baek","orcid":"https://orcid.org/0000-0002-7088-1478"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jun-Geol Baek","raw_affiliation_strings":["Korea University,Department of Industrial and Management Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Industrial and Management Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03020832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"0562","last_page":"0566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9961000084877014,"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":0.9961000084877014,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.9598000049591064,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6631109714508057},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6130132675170898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5812668800354004},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5429044365882874},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5416515469551086},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5201752185821533},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5181249976158142},{"id":"https://openalex.org/keywords/high-resolution","display_name":"High resolution","score":0.4779896140098572},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4520927369594574},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.44645795226097107},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3241409659385681},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13655057549476624},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.13306310772895813},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.10303470492362976},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06042492389678955}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6631109714508057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6130132675170898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5812668800354004},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5429044365882874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5416515469551086},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5201752185821533},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5181249976158142},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.4779896140098572},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4520927369594574},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.44645795226097107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3241409659385681},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13655057549476624},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.13306310772895813},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.10303470492362976},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06042492389678955},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic64266.2025.10920808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic64266.2025.10920808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2948982773","https://openalex.org/W2970520611","https://openalex.org/W3034328552","https://openalex.org/W3040266635","https://openalex.org/W3169651898","https://openalex.org/W4312605624","https://openalex.org/W4386065385","https://openalex.org/W4386065512","https://openalex.org/W4386065763","https://openalex.org/W4390875033"],"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":{"Zero-shot":[0],"anomaly":[1,64],"segmentation":[2],"(ZSAS)":[3],"is":[4,21,42],"crucial":[5],"for":[6,16,135],"detecting":[7],"and":[8,35,70,116,139,166,190,195],"localizing":[9],"defects":[10],"in":[11,24,59,103,131,144],"target":[12],"datasets":[13],"without":[14,119],"need":[15],"training":[17,34],"samples.":[18],"This":[19],"approach":[20,94],"particularly":[22],"valuable":[23],"industrial":[25,104,187,200],"quality":[26],"control,":[27],"where":[28],"there":[29],"are":[30],"distributional":[31],"shifts":[32],"between":[33],"operational":[36],"environments":[37],"or":[38],"when":[39],"data":[40],"access":[41],"restricted.":[43],"Recent":[44],"vision-language":[45],"models":[46],"have":[47],"demonstrated":[48,181],"strong":[49,193],"zero-shot":[50],"performance":[51,194],"across":[52,198],"various":[53],"visual":[54],"tasks.":[55,106],"However,":[56],"the":[57,60,132,145],"variations":[58],"granularity":[61],"of":[62,159,164,173,177],"local":[63,151],"regions":[65],"due":[66],"to":[67,79,83,100,113,148],"resolution":[68],"changes":[69],"their":[71],"focus":[72],"on":[73,121,185],"class":[74],"semantics":[75],"make":[76],"it":[77],"challenging":[78],"directly":[80],"apply":[81],"them":[82],"ZSAS.":[84],"To":[85],"address":[86],"these":[87],"issues,":[88],"we":[89,108,126],"propose":[90],"DHR-CLIP,":[91],"a":[92],"novel":[93],"that":[95],"incorporates":[96],"dynamic":[97],"high-resolution":[98],"processing":[99],"enhance":[101],"ZSAS":[102],"inspection":[105],"Additionally,":[107],"adapt":[109],"object-agnostic":[110],"prompt":[111,129,168],"design":[112],"detect":[114],"normal":[115],"anomalous":[117],"patterns":[118],"relying":[120],"specific":[122],"object":[123],"semantics.":[124],"Finally,":[125],"implement":[127],"deep-text":[128],"tuning":[130],"text":[133,167],"encoder":[134,147],"refined":[136],"textual":[137],"representations":[138],"employ":[140],"V-V":[141],"attention":[142],"layers":[143],"vision":[146],"capture":[149],"detailed":[150],"features.":[152],"Our":[153],"integrated":[154],"framework":[155],"enables":[156],"effective":[157],"identification":[158],"fine-grained":[160],"anomalies":[161],"through":[162,182],"refinement":[163],"image":[165],"design,":[169],"providing":[170],"precise":[171],"localization":[172],"defects.":[174],"The":[175],"effectiveness":[176],"DHR-CLIP":[178],"has":[179],"been":[180],"comprehensive":[183],"experiments":[184],"real-world":[186],"datasets,":[188],"MVTecAD":[189],"VisA,":[191],"achieving":[192],"generalization":[196],"capabilities":[197],"diverse":[199],"scenarios.":[201]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}