{"id":"https://openalex.org/W4416163454","doi":"https://doi.org/10.1109/wacv61042.2026.00610","title":"VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion","display_name":"VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416163454","doi":"https://doi.org/10.1109/wacv61042.2026.00610"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbilu.uni.lu/handle/10993/67845","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057644494","display_name":"Samet Hi\u00e7s\u00f6nmez","orcid":"https://orcid.org/0000-0002-4831-4362"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Samet Hicsonmez","raw_affiliation_strings":["University of Luxembourg Luxembourg,Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg Luxembourg,Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079812103","display_name":"Abd El Rahman Shabayek","orcid":"https://orcid.org/0000-0001-8730-3765"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Abd El Rahman Shabayek","raw_affiliation_strings":["University of Luxembourg Luxembourg,Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg Luxembourg,Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083368272","display_name":"Djamila Aouada","orcid":"https://orcid.org/0000-0002-7576-2064"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Djamila Aouada","raw_affiliation_strings":["University of Luxembourg Luxembourg,Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg Luxembourg,Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I186903577"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02095968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6309","last_page":"6319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9753000140190125,"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":0.9753000140190125,"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":0.0071000000461936,"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":0.0035000001080334187,"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":0.7116000056266785},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6150000095367432},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6078000068664551},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5913000106811523},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5605000257492065},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5580999851226807},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5543000102043152},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48190000653266907},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4747999906539917}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7116000056266785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.65829998254776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6435999870300293},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6150000095367432},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6078000068664551},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5913000106811523},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5580999851226807},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5543000102043152},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48190000653266907},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4221000075340271},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3937999904155731},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C55128770","wikidata":"https://www.wikidata.org/wiki/Q5275440","display_name":"Diffusion map","level":4,"score":0.32249999046325684},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/wacv61042.2026.00610","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:orbilu.uni.lu:10993/67845","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/67845","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (2026); IEEE/CVF Winter Conference on Applications of Computer Vision 2026, Tucson, United States [US], 06 - 10 March 2026","raw_type":"peer reviewed"},{"id":"pmh:oai:arXiv.org:2511.08173","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.08173","pdf_url":"https://arxiv.org/pdf/2511.08173","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.08173","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.08173","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:orbilu.uni.lu:10993/67845","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/67845","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (2026); IEEE/CVF Winter Conference on Applications of Computer Vision 2026, Tucson, United States [US], 06 - 10 March 2026","raw_type":"peer reviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Detecting":[0],"visual":[1,19],"anomalies":[2],"in":[3],"diverse,":[4],"multi-class":[5,18],"real-world":[6],"images":[7],"is":[8,142],"a":[9,15,25,31,42,46,100],"significant":[10],"challenge.":[11],"We":[12],"introduce":[13],"VLMDiff,":[14,79],"novel":[16],"unsupervised":[17],"anomaly":[20,37,108],"detection":[21],"framework.":[22],"It":[23],"integrates":[24],"Latent":[26],"Diffusion":[27],"Model":[28,33],"(LDM)":[29],"with":[30,45],"Vision-Language":[32],"(VLM)":[34],"for":[35,57,106],"enhanced":[36],"localization":[38],"and":[39,71,130],"detection.":[40,109],"Specifically,":[41],"pretrained":[43],"VLM":[44],"simple":[47],"prompt":[48],"extracts":[49],"detailed":[50],"image":[51,103],"descriptions,":[52],"serving":[53],"as":[54],"additional":[55,91],"conditioning":[56],"LDM":[58],"training.":[59,92],"Current":[60],"diffusion-based":[61,139],"methods":[62],"rely":[63],"on":[64,126,133],"synthetic":[65],"noise":[66],"generation,":[67],"limiting":[68],"their":[69],"generalization":[70],"requiring":[72],"per-class":[73],"model":[74],"training,":[75],"which":[76],"hinders":[77],"scalability.":[78],"however,":[80],"leverages":[81],"VLMs":[82],"to":[83,123],"obtain":[84],"normal":[85,102],"captions":[86],"without":[87],"manual":[88],"annotations":[89],"or":[90],"These":[93],"descriptions":[94],"condition":[95],"the":[96,116,127,134],"diffusion":[97],"model,":[98],"learning":[99],"robust":[101],"feature":[104],"representation":[105],"multiclass":[107],"Our":[110],"method":[111],"achieves":[112],"competitive":[113],"performance,":[114],"improving":[115],"pixel-level":[117],"Per-Region-Overlap":[118],"(PRO)":[119],"metric":[120],"by":[121],"up":[122],"25":[124],"points":[125,132],"Real-IAD":[128],"dataset":[129],"8":[131],"COCO-AD":[135],"dataset,":[136],"outperforming":[137],"state-of-the-art":[138],"approaches.":[140],"Code":[141],"available":[143],"at":[144],"https://github.com/giddyyupp/VLMDiff.":[145]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-13T00:00:00"}