{"id":"https://openalex.org/W7134829870","doi":"https://doi.org/10.48550/arxiv.2603.07952","title":"VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer","display_name":"VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134829870","doi":"https://doi.org/10.48550/arxiv.2603.07952"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.07952","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128661078","display_name":"Yanning Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Yanning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114250913","display_name":"Peiyuan Li","orcid":"https://orcid.org/0009-0002-0365-1602"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Peiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128638568","display_name":"Zirui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zirui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122097001","display_name":"Yitong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ruan, Yanran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruan, Yanran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128649381","display_name":"Jianfeng Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Jianfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128646354","display_name":"Ke Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28980961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9526000022888184,"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":0.9526000022888184,"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":0.014499999582767487,"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":0.006899999920278788,"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":0.7878000140190125},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6643999814987183},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5378000140190125},{"id":"https://openalex.org/keywords/normality","display_name":"Normality","score":0.5105999708175659},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.48030000925064087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43880000710487366}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7878000140190125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912999749183655},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6643999814987183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5472000241279602},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5378000140190125},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.529699981212616},{"id":"https://openalex.org/C2776157432","wikidata":"https://www.wikidata.org/wiki/Q1375683","display_name":"Normality","level":2,"score":0.5105999708175659},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.48030000925064087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3668999969959259},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2791999876499176}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.07952","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2603.07952","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07952","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:doi:10.48550/arxiv.2603.07952","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"sustainable_development_goals":[{"score":0.616325855255127,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"anomaly":[1,13,118,154,163],"detection":[2,164],"(ZSAD)":[3],"requires":[4],"detecting":[5],"and":[6,34,53,62,76,100,117,134,148,168,171,184],"localizing":[7],"anomalies":[8],"without":[9],"access":[10],"to":[11,59,96,122,174],"target-class":[12],"samples.":[14],"Mainstream":[15],"methods":[16],"rely":[17],"on":[18,49,84,160],"vision-language":[19],"models":[20],"(VLMs)":[21],"such":[22,178],"as":[23,179],"CLIP:":[24],"they":[25],"build":[26],"hand-crafted":[27],"or":[28],"learned":[29],"prompt":[30],"sets":[31],"for":[32,41],"normal":[33],"abnormal":[35],"semantics,":[36],"then":[37],"compute":[38],"image-text":[39],"similarities":[40],"open-set":[42],"discrimination.":[43],"While":[44],"effective,":[45],"this":[46],"paradigm":[47],"depends":[48],"a":[50,79,93,129,135],"text":[51,72],"encoder":[52,183],"cross-modal":[54],"alignment,":[55],"which":[56],"can":[57],"lead":[58],"training":[60],"instability":[61],"parameter":[63],"redundancy.":[64],"This":[65],"work":[66],"revisits":[67],"the":[68,71,146,180],"necessity":[69],"of":[70,115],"branch":[73],"in":[74],"ZSAD":[75],"presents":[77],"VisualAD,":[78],"purely":[80],"visual":[81],"framework":[82],"built":[83],"Vision":[85],"Transformers.":[86],"We":[87],"introduce":[88],"two":[89],"learnable":[90],"tokens":[91,106],"within":[92],"frozen":[94],"backbone":[95],"directly":[97],"encode":[98],"normality":[99,116],"abnormality.":[101],"Through":[102],"multi-layer":[103],"self-attention,":[104],"these":[105],"interact":[107],"with":[108],"patch":[109,151],"tokens,":[110,147],"gradually":[111],"acquiring":[112],"high-level":[113],"notions":[114],"while":[119],"guiding":[120],"patches":[121],"highlight":[123],"anomaly-related":[124],"cues.":[125],"Additionally,":[126],"we":[127],"incorporate":[128],"Spatial-Aware":[130],"Cross-Attention":[131],"(SCA)":[132],"module":[133],"lightweight":[136],"Self-Alignment":[137],"Function":[138],"(SAF):":[139],"SCA":[140],"injects":[141],"fine-grained":[142],"spatial":[143],"information":[144],"into":[145],"SAF":[149],"recalibrates":[150],"features":[152],"before":[153],"scoring.":[155],"VisualAD":[156],"achieves":[157],"state-of-the-art":[158],"performance":[159],"13":[161],"zero-shot":[162],"benchmarks":[165],"spanning":[166],"industrial":[167],"medical":[169],"domains,":[170],"adapts":[172],"seamlessly":[173],"pretrained":[175],"vision":[176],"backbones":[177],"CLIP":[181],"image":[182],"DINOv2.":[185],"Code:":[186],"https://github.com/7HHHHH/VisualAD":[187]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-03-11T00:00:00"}