{"id":"https://openalex.org/W4417006824","doi":"https://doi.org/10.48550/arxiv.2512.02520","title":"On the Problem of Consistent Anomalies in Zero-Shot Anomaly Detection","display_name":"On the Problem of Consistent Anomalies in Zero-Shot Anomaly Detection","publication_year":2025,"publication_date":"2025-12-02","ids":{"openalex":"https://openalex.org/W4417006824","doi":"https://doi.org/10.48550/arxiv.2512.02520"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2512.02520","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.02520","pdf_url":"https://arxiv.org/pdf/2512.02520","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.02520","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104220988","display_name":"Tai Le-Gia","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Le-Gia, Tai","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5104220988"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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":0.9509000182151794,"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":0.9509000182151794,"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":0.008999999612569809,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.002199999988079071,"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":0.6589999794960022},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.551800012588501},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5159000158309937},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5152000188827515},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.49810001254081726},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4374000132083893},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41100001335144043},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39570000767707825}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6589999794960022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6134999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5533000230789185},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5152000188827515},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49810001254081726},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41100001335144043},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3652999997138977},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.02520","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.02520","pdf_url":"https://arxiv.org/pdf/2512.02520","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"},{"id":"doi:10.48550/arxiv.2512.02520","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.02520","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.02520","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.02520","pdf_url":"https://arxiv.org/pdf/2512.02520","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":"text"},"sustainable_development_goals":[],"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":[1,176,183],"classification":[2],"and":[3,11,24,38,45,72,90,102,129,138,179,196,216],"segmentation":[4,184],"(AC/AS)":[5],"aim":[6],"to":[7,30,154],"detect":[8],"anomalous":[9],"samples":[10],"regions":[12],"without":[13,103,187],"any":[14,188],"training":[15,190],"data,":[16],"a":[17,56,117,160,172],"capability":[18],"increasingly":[19],"crucial":[20],"in":[21,43,59,106],"industrial":[22],"inspection":[23],"medical":[25,156],"imaging.":[26],"This":[27,170],"dissertation":[28,212],"aims":[29],"investigate":[31],"the":[32,51,70,126,144,220],"core":[33],"challenges":[34],"of":[35,53,75,146],"zero-shot":[36,174,198,221],"AC/AS":[37,222],"presents":[39],"principled":[40],"solutions":[41,218],"rooted":[42],"theory":[44],"algorithmic":[46],"design.":[47],"We":[48,113],"first":[49],"formalize":[50],"problem":[52],"consistent":[54,104,122,147],"anomalies,":[55],"failure":[57],"mode":[58],"which":[60],"recurring":[61],"similar":[62,111],"anomalies":[63,105,123],"systematically":[64],"bias":[65],"distance-based":[66],"methods.":[67],"By":[68],"analyzing":[69],"statistical":[71],"geometric":[73],"behavior":[74],"patch":[76],"representations":[77],"from":[78],"pre-trained":[79],"Vision":[80],"Transformers,":[81],"we":[82,150,193],"identify":[83],"two":[84],"key":[85],"phenomena":[86],"-":[87,92],"similarity":[88,127],"scaling":[89,128],"neighbor-burnout":[91,130],"that":[93,181,202],"describe":[94],"how":[95],"relationships":[96],"among":[97],"normal":[98],"patches":[99],"change":[100],"with":[101],"settings":[107],"characterized":[108],"by":[109,158,200],"highly":[110],"objects.":[112],"then":[114],"introduce":[115],"CoDeGraph,":[116],"graph-based":[118],"framework":[119,153],"for":[120,167,219],"filtering":[121],"built":[124],"on":[125],"phenomena.":[131],"Through":[132],"multi-stage":[133],"graph":[134],"construction,":[135],"community":[136],"detection,":[137],"structured":[139],"refinement,":[140],"CoDeGraph":[141],"effectively":[142],"suppresses":[143],"influence":[145],"anomalies.":[148],"Next,":[149],"extend":[151],"this":[152,211],"3D":[155,175,189],"imaging":[157],"proposing":[159],"training-free,":[161],"computationally":[162],"efficient":[163],"volumetric":[164,182],"tokenization":[165],"strategy":[166],"MRI":[168],"data.":[169],"enables":[171],"genuinely":[173],"detection":[177],"pipeline":[178],"shows":[180],"is":[185],"achievable":[186],"samples.":[191],"Finally,":[192],"bridge":[194],"batch-based":[195],"text-based":[197],"methods":[199],"demonstrating":[201],"CoDeGraph-derived":[203],"pseudo-masks":[204],"can":[205],"supervise":[206],"prompt-driven":[207],"vision-language":[208],"models.":[209],"Together,":[210],"provides":[213],"theoretical":[214],"understanding":[215],"practical":[217],"problem.":[223]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-04T00:00:00"}