{"id":"https://openalex.org/W4415137788","doi":"https://doi.org/10.1109/iccv51701.2025.02072","title":"Alleviating Textual Reliance in Medical Language-Guided Segmentation via Prototype-Driven Semantic Approximation","display_name":"Alleviating Textual Reliance in Medical Language-Guided Segmentation via Prototype-Driven Semantic Approximation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415137788","doi":"https://doi.org/10.1109/iccv51701.2025.02072"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.11055","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089664822","display_name":"Shuchang Ye","orcid":"https://orcid.org/0009-0006-1935-1953"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shuchang Ye","raw_affiliation_strings":["The University of Sydney,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077006200","display_name":"Usman Naseem","orcid":"https://orcid.org/0000-0003-0191-7171"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Usman Naseem","raw_affiliation_strings":["Macquarie University,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University,Sydney,Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022712090","display_name":"Mingyuan Meng","orcid":"https://orcid.org/0000-0002-9562-1613"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mingyuan Meng","raw_affiliation_strings":["The University of Sydney,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100614820","display_name":"Jinman Kim","orcid":"https://orcid.org/0000-0001-5960-1060"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jinman Kim","raw_affiliation_strings":["The University of Sydney,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24529571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22316","last_page":"22326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9854000210762024,"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/T10028","display_name":"Topic Modeling","score":0.9854000210762024,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9815000295639038,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7656000256538391},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7466999888420105},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6399999856948853},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5236999988555908},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.45829999446868896},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3977000117301941}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7656000256538391},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7466999888420105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465999722480774},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6399999856948853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5853999853134155},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45829999446868896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3357999920845032},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2849000096321106},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.2574999928474426}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.11055","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.11055","pdf_url":"https://arxiv.org/pdf/2507.11055","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.11055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.11055","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":"pmh:oai:arXiv.org:2507.11055","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.11055","pdf_url":"https://arxiv.org/pdf/2507.11055","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Medical":[0],"language-guided":[1,96,171],"segmentation,":[2,13],"integrating":[3],"textual":[4,101,122,137,153,157],"clinical":[5,76],"reports":[6],"as":[7,33],"auxiliary":[8],"guidance":[9,120,149],"to":[10,32,63,115],"enhance":[11],"image":[12],"has":[14],"demonstrated":[15],"significant":[16],"improvements":[17],"over":[18],"unimodal":[19],"approaches.":[20],"However,":[21],"its":[22,72,104],"inherent":[23],"reliance":[24],"on":[25,161],"paired":[26,46,69],"image-text":[27],"input,":[28,154],"which":[29,146],"we":[30,87,106],"refer":[31],"``textual":[34],"reliance\",":[35],"presents":[36],"two":[37],"fundamental":[38],"limitations:":[39],"1)":[40],"many":[41],"medical":[42],"segmentation":[43,79,97],"datasets":[44],"lack":[45],"reports,":[47,70],"leaving":[48],"a":[49,108,126,143],"substantial":[50],"portion":[51],"of":[52,66,118],"image-only":[53],"data":[54],"underutilized":[55],"for":[56,95,150],"training;":[57],"and":[58,128,164],"2)":[59],"inference":[60],"is":[61,176],"limited":[62,174],"retrospective":[64],"analysis":[65],"cases":[67],"with":[68],"limiting":[71],"applicability":[73],"in":[74],"most":[75],"scenarios":[77],"where":[78],"typically":[80],"precedes":[81],"reporting.":[82],"To":[83],"address":[84],"these":[85],"limitations,":[86],"propose":[88],"ProLearn,":[89],"the":[90],"first":[91],"Prototype-driven":[92,110],"Learning":[93],"framework":[94],"that":[98,167],"fundamentally":[99],"alleviates":[100],"reliance.":[102,158],"At":[103],"core,":[105],"introduce":[107],"novel":[109],"Semantic":[111],"Approximation":[112],"(PSA)":[113],"module":[114],"enable":[116],"approximation":[117],"semantic":[119,148],"from":[121,136],"input.":[123],"PSA":[124],"initializes":[125],"discrete":[127],"compact":[129],"prototype":[130],"space":[131],"by":[132],"distilling":[133],"segmentation-relevant":[134],"semantics":[135],"reports.":[138],"Once":[139],"initialized,":[140],"it":[141],"supports":[142],"query-and-respond":[144],"mechanism":[145],"approximates":[147],"images":[151],"without":[152],"thereby":[155],"alleviating":[156],"Extensive":[159],"experiments":[160],"QaTa-COV19,":[162],"MosMedData+":[163],"Kvasir-SEG":[165],"demonstrate":[166],"ProLearn":[168],"outperforms":[169],"state-of-the-art":[170],"methods":[172],"when":[173],"text":[175],"available.":[177]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-14T00:00:00"}