{"id":"https://openalex.org/W7160502451","doi":"https://doi.org/10.48550/arxiv.2605.05161","title":"Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging","display_name":"Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160502451","doi":"https://doi.org/10.48550/arxiv.2605.05161"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.05161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05161","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.05161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135559183","display_name":"Bernhard Kainz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kainz, Bernhard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135579425","display_name":"Johanna P Mueller","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mueller, Johanna P","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034283416","display_name":"Matthew Baugh","orcid":"https://orcid.org/0000-0001-6252-7658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baugh, Matthew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135619081","display_name":"Cosmin Bercea","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bercea, Cosmin","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":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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.580299973487854,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.580299973487854,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05689999833703041,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.055399999022483826,"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/goldilocks-principle","display_name":"Goldilocks principle","score":0.7039999961853027},{"id":"https://openalex.org/keywords/mcnemars-test","display_name":"McNemar's test","score":0.6001999974250793},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5212000012397766},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.476500004529953},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42649999260902405},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.3991999924182892},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.362199991941452},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.36149999499320984}],"concepts":[{"id":"https://openalex.org/C177321328","wikidata":"https://www.wikidata.org/wiki/Q13580479","display_name":"Goldilocks principle","level":2,"score":0.7039999961853027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6201000213623047},{"id":"https://openalex.org/C186282968","wikidata":"https://www.wikidata.org/wiki/Q1434261","display_name":"McNemar's test","level":2,"score":0.6001999974250793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5827999711036682},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5212000012397766},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.362199991941452},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3447999954223633},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C2776825360","wikidata":"https://www.wikidata.org/wiki/Q1411921","display_name":"Vagueness","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C68767595","wikidata":"https://www.wikidata.org/wiki/Q1677999","display_name":"Contiguity","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.251800000667572},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.05161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05161","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.05161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05161","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Zero-shot":[0],"anomaly":[1],"localisation":[2,31,92],"via":[3,98],"vision-language":[4],"models":[5],"(VLMs)":[6],"offers":[7],"a":[8,33,54,119,143],"compelling":[9],"approach":[10],"for":[11,72],"rare":[12],"pathology":[13],"detection,":[14],"yet":[15],"its":[16],"performance":[17],"is":[18,172],"fundamentally":[19],"limited":[20],"by":[21],"the":[22,85,105,127],"absence":[23],"of":[24,48],"healthy":[25],"anatomical":[26],"context.":[27],"We":[28,51,102],"reformulate":[29],"zero-shot":[30,148],"as":[32],"comparative":[34,64,123],"inference":[35],"problem":[36],"in":[37,58,122],"which":[38],"anomalies":[39],"are":[40],"identified":[41],"through":[42,108],"structured":[43],"comparison":[44],"against":[45],"reference":[46,74,89],"distributions":[47],"normal":[49],"anatomy.":[50],"introduce":[52],"WALDO,":[53],"training-free":[55],"framework":[56],"grounded":[57],"optimal":[59],"transport":[60],"theory":[61],"that":[62,113],"enables":[63],"reasoning":[65],"through:":[66],"(i)":[67],"entropy-weighted":[68],"Sliced":[69],"Wasserstein":[70],"distances":[71],"anatomically-aware":[73],"selection":[75],"from":[76],"DINOv2":[77],"patch":[78],"distributions,":[79],"(ii)":[80],"Goldilocks":[81,106],"zone":[82],"sampling":[83],"exploiting":[84],"non-monotonic":[86],"relationship":[87],"between":[88],"similarity":[90,117],"and":[91,94,111,158],"accuracy,":[93],"(iii)":[95],"self-consistency":[96],"aggregation":[97],"weighted":[99],"non-maximum":[100],"suppression.":[101],"theoretically":[103],"analyse":[104],"effect":[107],"distributional":[109],"divergence,":[110],"show":[112],"references":[114],"with":[115,133],"moderate":[116],"minimize":[118],"bias-variance":[120],"trade-off":[121],"visual":[124],"reasoning.":[125],"On":[126],"NOVA":[128],"brain":[129],"MRI":[130],"benchmark,":[131],"WALDO":[132],"Qwen2.5-VL-72B":[134],"achieves":[135,156,160],"$43.5_{\\pm1.6}\\%$":[136],"mAP@30":[137],"(95\\%":[138],"CI:":[139],"[40.4,":[140],"46.7]),":[141],"representing":[142],"19\\%":[144],"relative":[145],"improvement":[146],"over":[147],"baselines.":[149],"Cross-model":[150],"evaluation":[151],"shows":[152],"consistent":[153],"gains:":[154],"GPT-4o":[155],"$32.0_{\\pm6.5}\\%$":[157],"Qwen3-VL-32B":[159],"$32.0_{\\pm6.6}\\%$":[161],"mAP@30.":[162],"Paired":[163],"McNemar":[164],"tests":[165],"confirm":[166],"statistical":[167],"significance":[168],"($p<0.01$).":[169],"Source":[170],"code":[171],"available":[173],"at":[174],"https://github.com/bkainz/WALDO_MICCAI26_demo":[175],".":[176]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-08T00:00:00"}