{"id":"https://openalex.org/W7131425117","doi":"https://doi.org/10.48550/arxiv.2602.18766","title":"Initialization matters in few-shot adaptation of vision-language models for histopathological image classification","display_name":"Initialization matters in few-shot adaptation of vision-language models for histopathological image classification","publication_year":2026,"publication_date":"2026-02-21","ids":{"openalex":"https://openalex.org/W7131425117","doi":"https://doi.org/10.48550/arxiv.2602.18766"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.18766","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18766","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":"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.2602.18766","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078997558","display_name":"Pablo Meseguer","orcid":"https://orcid.org/0000-0001-7821-6168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meseguer, Pablo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067714499","display_name":"Roc\u00edo del Amor","orcid":"https://orcid.org/0000-0002-5342-2093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"del Amor, Roc\u00edo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123515472","display_name":"V Naranjo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naranjo, Valery","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/T10862","display_name":"AI in cancer detection","score":0.8098000288009644,"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/T10862","display_name":"AI in cancer detection","score":0.8098000288009644,"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":0.042899999767541885,"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/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.031700000166893005,"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/initialization","display_name":"Initialization","score":0.8353999853134155},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7925999760627747},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6176999807357788},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5924999713897705},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5856999754905701},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5667999982833862},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5020999908447266},{"id":"https://openalex.org/keywords/linear-classifier","display_name":"Linear classifier","score":0.49559998512268066}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8353999853134155},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7925999760627747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300999760627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7272999882698059},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6176999807357788},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5924999713897705},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5856999754905701},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5667999982833862},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5020999908447266},{"id":"https://openalex.org/C139532973","wikidata":"https://www.wikidata.org/wiki/Q2679259","display_name":"Linear classifier","level":3,"score":0.49559998512268066},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4546999931335449},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.18766","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18766","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":"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.2602.18766","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.18766","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":"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":[{"score":0.784490168094635,"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":{"Vision":[0],"language":[1],"models":[2],"(VLM)":[3],"pre-trained":[4],"on":[5,70,74,88,99],"datasets":[6],"of":[7,17,48,58,76,115,131,155,166],"histopathological":[8],"image-caption":[9],"pairs":[10],"enabled":[11],"zero-shot":[12,121],"slide-level":[13,78],"classification.":[14],"The":[15],"ability":[16],"VLM":[18,133],"image":[19,34],"encoders":[20],"to":[21,54,111,142,158],"extract":[22],"discriminative":[23],"features":[24],"also":[25],"opens":[26],"the":[27,46,55,59,77,113,128,132,137,153],"door":[28],"for":[29,32,175],"supervised":[30],"fine-tuning":[31],"whole-slide":[33],"(WSI)":[35],"classification,":[36],"ideally":[37],"using":[38],"few":[39],"labeled":[40],"samples.":[41],"Slide-level":[42],"prediction":[43,122],"frameworks":[44,68],"require":[45],"incorporation":[47],"multiple":[49,149],"instance":[50],"learning":[51,95],"(MIL)":[52],"due":[53],"gigapixel":[56],"size":[57],"WSI.":[60],"Following":[61],"patch-level":[62],"feature":[63],"extraction":[64],"and":[65,168],"aggregation,":[66],"MIL":[67,124],"rely":[69],"linear":[71],"classifiers":[72],"trained":[73],"top":[75],"aggregated":[79],"features.":[80],"Classifier":[81],"weight":[82,160],"initialization":[83,118,161],"has":[84],"a":[85],"large":[86],"influence":[87],"Linear":[89],"Probing":[90],"performance":[91,167],"in":[92,123,164,170],"efficient":[93],"transfer":[94],"(ETL)":[96],"approaches":[97],"based":[98],"few-shot":[100,173],"learning.":[101],"In":[102],"this":[103],"work,":[104],"we":[105,151],"propose":[106],"Zero-Shot":[107],"Multiple-Instance":[108],"Learning":[109],"(ZS-MIL)":[110],"address":[112],"limitations":[114],"random":[116],"classifier":[117],"that":[119],"underperform":[120],"problems.":[125],"ZS-MIL":[126,156],"uses":[127],"class-level":[129],"embeddings":[130],"text":[134],"encoder":[135],"as":[136],"classification":[138],"layer's":[139],"starting":[140],"point":[141],"compute":[143],"each":[144],"sample's":[145],"bag-level":[146],"probabilities.":[147],"Through":[148],"experiments,":[150],"demonstrate":[152],"robustness":[154],"compared":[157],"well-known":[159],"techniques":[162],"both":[163],"terms":[165],"variability":[169],"an":[171],"ETL":[172],"scenario":[174],"subtyping":[176],"prediction.":[177]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-02-26T00:00:00"}