{"id":"https://openalex.org/W4417464888","doi":"https://doi.org/10.1109/wacv61042.2026.00734","title":"Improvise, Adapt, Overcome \u2014 Telescopic Adapters for Efficient Fine-tuning of Vision Language Models in Medical Imaging","display_name":"Improvise, Adapt, Overcome \u2014 Telescopic Adapters for Efficient Fine-tuning of Vision Language Models in Medical Imaging","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417464888","doi":"https://doi.org/10.1109/wacv61042.2026.00734"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.13855","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052074125","display_name":"Ujjwal M. Mishra","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ujjwal Mishra","raw_affiliation_strings":["Indian Institute of Technology,Centre for Artificial Intelligence and Robotics,Mandi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Centre for Artificial Intelligence and Robotics,Mandi,India","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102602444","display_name":"Vinita Shukla","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinita Shukla","raw_affiliation_strings":["Indian Institute of Technology,Centre for Artificial Intelligence and Robotics,Mandi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Centre for Artificial Intelligence and Robotics,Mandi,India","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091700001","display_name":"Praful Hambarde","orcid":"https://orcid.org/0000-0002-7976-9095"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Praful Hambarde","raw_affiliation_strings":["Indian Institute of Technology,Centre for Artificial Intelligence and Robotics,Mandi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Centre for Artificial Intelligence and Robotics,Mandi,India","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052526237","display_name":"Amit Shukla","orcid":"https://orcid.org/0000-0002-0537-5851"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amit Shukla","raw_affiliation_strings":["Indian Institute of Technology,Centre for Artificial Intelligence and Robotics,Mandi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Centre for Artificial Intelligence and Robotics,Mandi,India","institution_ids":["https://openalex.org/I4210121405"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210121405"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02634099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7605","last_page":"7615"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2825999855995178,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2825999855995178,"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/T10862","display_name":"AI in cancer detection","score":0.10509999841451645,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09669999778270721,"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/bottleneck","display_name":"Bottleneck","score":0.5971999764442444},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.5339999794960022},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5253000259399414},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.43950000405311584},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4350000023841858},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.41830000281333923},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4032999873161316},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577000260353088},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4821000099182129},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4032999873161316},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3959999978542328},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3675000071525574},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C2992165143","wikidata":"https://www.wikidata.org/wiki/Q234904","display_name":"Medical ultrasound","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.257099986076355},{"id":"https://openalex.org/C139458680","wikidata":"https://www.wikidata.org/wiki/Q12184942","display_name":"Interoperation","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2517000138759613},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.13855","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13855","pdf_url":"https://arxiv.org/pdf/2512.13855","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.13855","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.13855","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":"pmh:oai:arXiv.org:2512.13855","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13855","pdf_url":"https://arxiv.org/pdf/2512.13855","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417464888.pdf","grobid_xml":"https://content.openalex.org/works/W4417464888.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Adapting":[0],"Vision":[1],"Language":[2],"Segmentation":[3],"Models":[4],"(VLSMs)":[5],"to":[6,33,53,60],"medical":[7,105,145],"imaging":[8],"domains":[9],"requires":[10],"significant":[11],"computational":[12],"overhead":[13],"when":[14],"using":[15],"conventional":[16],"fine-tuning":[17],"approaches.":[18],"Existing":[19],"Parameter-Efficient":[20],"Fine-Tuning":[21],"(PEFT)":[22],"methods":[23],"apply":[24],"uniform":[25],"adapter":[26,56,77],"dimensions":[27,78],"across":[28,102],"all":[29],"transformer":[30,62],"layers,":[31,131],"leading":[32],"suboptimal":[34],"parameter":[35],"allocation":[36],"and":[37,73,85,113],"reduced":[38],"adaptation":[39,127],"efficiency.":[40],"We":[41],"introduce":[42],"Telescopic":[43,97],"Adapters,":[44],"a":[45,140],"novel":[46],"PEFT":[47],"framework":[48],"that":[49,121],"employs":[50],"depth-aware":[51],"scaling":[52,135],"progressively":[54],"increase":[55],"capacity":[57,128],"from":[58],"shallow":[59,130],"deep":[61],"layers.":[63],"Our":[64,137],"method":[65],"integrates":[66],"lightweight":[67],"bottleneck":[68],"modules":[69],"within":[70],"CLIPSeg\u2019s":[71],"vision":[72],"text":[74],"encoders,":[75],"with":[76],"dynamically":[79],"scaled":[80],"based":[81],"on":[82],"layer":[83],"depth":[84],"semantic":[86],"relevance.":[87],"Using":[88],"only":[89],"613k":[90],"trainable":[91],"parameters\u2014244\u00d7":[92],"fewer":[93],"than":[94,129],"end-to-end":[95],"fine-tuning,":[96,147],"Adapters":[98],"achieve":[99],"superior":[100],"performance":[101],"five":[103],"diverse":[104],"datasets":[106],"spanning":[107],"polyp":[108],"segmentation,":[109],"skin":[110],"lesion":[111],"detection,":[112],"breast":[114],"ultrasound":[115],"imaging.":[116],"Comprehensive":[117],"ablation":[118],"studies":[119],"demonstrate":[120],"deeper":[122],"layers":[123],"require":[124],"substantially":[125],"more":[126],"validating":[132],"our":[133],"telescopic":[134],"hypothesis.":[136],"approach":[138],"establishes":[139],"new":[141],"paradigm":[142],"for":[143],"efficient":[144],"VLSM":[146],"enabling":[148],"deployment":[149],"in":[150],"resource-constrained":[151],"clinical":[152],"environments":[153],"while":[154],"maintaining":[155],"competitive":[156],"segmentation":[157],"accuracy.":[158]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-12-18T00:00:00"}