{"id":"https://openalex.org/W7155102096","doi":"https://doi.org/10.48550/arxiv.2604.18444","title":"ProtoCLIP: Prototype-Aligned Latent Refinement for Robust Zero-Shot Chest X-Ray Classification","display_name":"ProtoCLIP: Prototype-Aligned Latent Refinement for Robust Zero-Shot Chest X-Ray Classification","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7155102096","doi":"https://doi.org/10.48550/arxiv.2604.18444"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.18444","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18444","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":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.2604.18444","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048251357","display_name":"Florian Kittler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kittler, Florian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134170923","display_name":"Sheethal Bhat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhat, Sheethal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134126589","display_name":"Andreas Maier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maier, Andreas","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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9442999958992004,"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"}},"topics":[{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9442999958992004,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.017400000244379044,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.004900000058114529,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/construct","display_name":"Construct (python library)","score":0.5360999703407288},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5174999833106995},{"id":"https://openalex.org/keywords/chest-radiograph","display_name":"Chest radiograph","score":0.5084999799728394},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41339999437332153},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.3970000147819519},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.3917999863624573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3790999948978424},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.37209999561309814},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.3686000108718872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6427000164985657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5590000152587891},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C2781137159","wikidata":"https://www.wikidata.org/wiki/Q1283318","display_name":"Chest radiograph","level":3,"score":0.5084999799728394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4390000104904175},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41339999437332153},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3409000039100647},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.18444","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18444","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":"doi:10.48550/arxiv.2604.18444","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18444","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.6315178275108337,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"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],"vision-language":[1],"models":[2],"(VLMs)":[3],"have":[4],"shown":[5],"promise":[6],"for":[7,36],"chest":[8],"radiograph":[9],"classification,":[10],"but":[11],"their":[12],"performance":[13],"is":[14],"often":[15],"limited":[16],"by":[17,96],"confounding":[18],"label":[19],"co-occurrence,":[20],"long-tail":[21],"class":[22],"imbalance,":[23],"and":[24,47,79,128],"transfer":[25,135],"instability":[26],"under":[27],"domain":[28],"shift.":[29],"We":[30,65],"propose":[31],"ProtoCLIP,":[32],"a":[33,68,101,113],"refinement":[34],"strategy":[35],"CLIP-style":[37],"VLMs":[38,139],"that":[39,121],"improves":[40,94],"zero-shot":[41,134],"discrimination":[42,81],"through":[43],"targeted":[44],"data":[45],"curation":[46],"distilled":[48],"anchor":[49],"alignment.":[50],"Specifically,":[51],"we":[52],"construct":[53],"pathology-focused":[54],"training":[55],"subsets":[56],"with":[57,125],"curated":[58,126],"negative":[59],"samples":[60],"to":[61,72],"reduce":[62],"co-occurrence":[63],"bias.":[64],"also":[66],"introduce":[67],"representation-preserving":[69],"distillation":[70],"objective":[71],"stabilize":[73],"adaptation":[74],"while":[75],"maintaining":[76],"semantic":[77],"structure":[78],"improving":[80],"of":[82,116],"clinically":[83],"relevant":[84],"co-occurring":[85],"pathologies.":[86],"Evaluated":[87],"on":[88],"an":[89],"unseen":[90],"dataset":[91],"VinDr-CXR,":[92],"ProtoCLIP":[93,111],"AUC":[95,115],"2-10":[97],"percentage":[98],"points":[99],"over":[100],"strong":[102],"CLIP-based":[103],"baseline":[104],"across":[105],"multiple":[106],"findings.":[107],"For":[108],"pneumothorax":[109],"specifically,":[110],"achieves":[112],"state-of-the-art":[114],"0.94.":[117],"These":[118],"results":[119],"demonstrate":[120],"anchor-guided":[122],"refinement,":[123],"coupled":[124],"supervision":[127],"controlled":[129],"adaptation,":[130],"can":[131],"mitigate":[132],"common":[133],"failures":[136],"in":[137],"medical":[138],"without":[140],"requiring":[141],"large-scale":[142],"retraining.":[143]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-22T00:00:00"}