{"id":"https://openalex.org/W7133334157","doi":"https://doi.org/10.48550/arxiv.2603.00433","title":"TAP-SLF: Parameter-Efficient Adaptation of Vision Foundation Models for Multi-Task Ultrasound Image Analysis","display_name":"TAP-SLF: Parameter-Efficient Adaptation of Vision Foundation Models for Multi-Task Ultrasound Image Analysis","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133334157","doi":"https://doi.org/10.48550/arxiv.2603.00433"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00433","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00433","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":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.2603.00433","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127989181","display_name":"Hui Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091564313","display_name":"Libin Lan","orcid":"https://orcid.org/0000-0003-4754-813X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lan, Libin","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":0.3732999861240387,"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":0.3732999861240387,"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/T10727","display_name":"Ultrasound Imaging and Elastography","score":0.14839999377727509,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.12919999659061432,"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/overfitting","display_name":"Overfitting","score":0.8489000201225281},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5992000102996826},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5819000005722046},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5569000244140625},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5493000149726868},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.527899980545044},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43720000982284546},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.420199990272522}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8489000201225281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.746999979019165},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5819000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579000115394592},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5569000244140625},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5493000149726868},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.527899980545044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4494999945163727},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43720000982284546},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3443000018596649},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3240000009536743},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3188999891281128},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26460000872612}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00433","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00433","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":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.2603.00433","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00433","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":null,"license_id":null,"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":{"Executing":[0],"multiple":[1],"tasks":[2,153],"simultaneously":[3],"in":[4],"medical":[5,41,152],"image":[6,93],"analysis,":[7],"including":[8],"segmentation,":[9],"classification,":[10],"detection,":[11],"and":[12,21,47,66,82,109,189],"regression,":[13],"often":[14],"introduces":[15],"significant":[16],"challenges":[17],"regarding":[18],"model":[19,71],"generalizability":[20],"the":[22,67,105,118,128,133,160,175],"optimization":[23],"of":[24,70,117,127],"shared":[25,156],"feature":[26],"representations.":[27],"While":[28],"Vision":[29],"Foundation":[30],"Models":[31],"(VFMs)":[32],"provide":[33],"powerful":[34],"general":[35],"representations,":[36],"full":[37],"fine-tuning":[38,55],"on":[39,159,174],"limited":[40],"data":[42],"is":[43],"prone":[44],"to":[45,100,112,150],"overfitting":[46],"incurs":[48],"high":[49],"computational":[50],"costs.":[51],"Moreover,":[52],"existing":[53],"parameter-efficient":[54],"approaches":[56],"typically":[57],"adopt":[58],"task-agnostic":[59],"adaptation":[60,149],"protocols,":[61],"overlooking":[62],"both":[63],"task-specific":[64,102],"mechanisms":[65],"varying":[68],"sensitivity":[69],"layers":[72,116],"during":[73],"fine-tuning.":[74],"In":[75],"this":[76],"work,":[77],"we":[78],"propose":[79],"Task-Aware":[80],"Prompting":[81],"Selective":[83],"Layer":[84],"Fine-Tuning":[85],"(TAP-SLF),":[86],"a":[87,124,155],"unified":[88],"framework":[89],"for":[90,196],"multi-task":[91],"ultrasound":[92],"analysis.":[94],"TAP-SLF":[95,145,167],"incorporates":[96],"task-aware":[97,139,187],"soft":[98],"prompts":[99,140],"encode":[101],"priors":[103],"into":[104],"input":[106],"token":[107],"sequence":[108],"applies":[110],"LoRA":[111],"selected":[113],"specific":[114],"top":[115],"encoder.":[119],"This":[120],"strategy":[121],"updates":[122],"only":[123],"small":[125],"fraction":[126],"VFM":[129,148,198],"parameters":[130],"while":[131],"keeping":[132],"pre-trained":[134],"backbone":[135],"frozen.":[136],"By":[137],"combining":[138],"with":[141,172],"selective":[142,190],"high-layer":[143],"fine-tuning,":[144],"enables":[146],"efficient":[147,197],"diverse":[151],"within":[154],"backbone.":[157],"Results":[158],"FMC_UIA":[161],"2026":[162],"Challenge":[163],"test":[164],"set,":[165],"where":[166],"wins":[168],"fifth":[169],"place,":[170],"combined":[171],"evaluations":[173],"officially":[176],"released":[177],"training":[178],"dataset":[179],"using":[180],"an":[181],"8:2":[182],"train-test":[183],"split,":[184],"demonstrate":[185],"that":[186],"prompting":[188],"layer":[191],"tuning":[192],"are":[193],"effective":[194],"strategies":[195],"adaptation.":[199]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-04T00:00:00"}