{"id":"https://openalex.org/W7138012126","doi":"https://doi.org/10.1609/aaai.v40i31.39819","title":"Retriever Encoder Selection Matters for In-Context Learning-based Medical Segmentation","display_name":"Retriever Encoder Selection Matters for In-Context Learning-based Medical Segmentation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138012126","doi":"https://doi.org/10.1609/aaai.v40i31.39819"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i31.39819","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39819","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i31.39819","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129738283","display_name":"Fan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fan Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129743386","display_name":"Zhongyi Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongyi Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040047825","display_name":"Yongshun Gong","orcid":"https://orcid.org/0000-0003-3948-4471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongshun Gong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129691642","display_name":"Yilong Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilong Yin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5129738283"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28933632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"31","first_page":"26160","last_page":"26168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.4025999903678894,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.4025999903678894,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.15209999680519104,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.06120000034570694,"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":0.550599992275238},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5238999724388123},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5024999976158142},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.46230000257492065},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4602999985218048},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43779999017715454},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.3952000141143799},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.37770000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832099974155426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.605400025844574},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.482699990272522},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42289999127388},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2639000117778778}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i31.39819","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39819","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i31.39819","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39819","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"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":{"In-context":[0],"learning-based":[1],"medical":[2],"segmentation":[3,196],"(ICLM)":[4],"enables":[5],"foundation":[6],"models":[7],"to":[8,10,34,145,284],"generalize":[9],"unseen":[11],"cases":[12],"without":[13],"retraining.":[14],"To":[15,149,235],"enhance":[16],"performance":[17,87,273],"on":[18,65,171,177,266,287],"test":[19],"queries,":[20],"existing":[21],"methods":[22,59],"typically":[23],"follow":[24],"a":[25,30,42,93,127,181,231],"two-stage":[26],"process:":[27],"(1)":[28,78,117],"using":[29],"retrieval":[31,156],"encoder":[32,157,257],"(RE)":[33],"map":[35],"both":[36],"queries":[37],"and":[38,46,49,63,112,134,141,194,255,268,278],"training":[39,55],"samples":[40],"into":[41],"shared":[43],"feature":[44],"space,":[45],"(2)":[47,135],"retrieving":[48],"utilizing":[50],"the":[51,61,72,86,109,120,131,154,164,178,188,201,208],"top-k":[52],"most":[53],"similar":[54],"samples.":[56],"While":[57],"current":[58],"fix":[60],"RE":[62,75,90,110,121,129,147,166,183,224],"focus":[64],"optimizing":[66],"stage":[67,77],"(2),":[68],"we":[69,104,152,199,240],"show":[70,218],"that":[71,161,180],"choice":[73],"of":[74,85,108,211],"in":[76,99],"alone":[79],"can":[80,162],"account":[81],"for":[82,122,130,167],"over":[83],"70%":[84],"variation,":[88],"highlighting":[89],"selection":[91,111,158,233],"as":[92,230],"critical":[94],"yet":[95],"often":[96],"overlooked":[97],"factor":[98],"ICLM.":[100],"In":[101],"this":[102,150],"paper,":[103],"conduct":[105],"an":[106],"analysis":[107],"make":[113],"two":[114],"main":[115],"findings:":[116],"dynamically":[118],"selecting":[119,126],"each":[123,168],"query":[124,169],"outperforms":[125],"fixed":[128],"entire":[132],"task;":[133],"feature-space":[136],"heuristics":[137],"(e.g.,":[138],"intra-class":[139],"compactness":[140],"inter-class":[142],"separability)":[143],"fail":[144],"predict":[146],"quality.":[148],"end,":[151],"propose":[153,241],"instance-adaptive":[155],"(IRES)":[159],"method":[160],"select":[163],"optimal":[165],"based":[170,176],"output":[172],"predictions.":[173],"IRES":[174,270],"is":[175],"intuition":[179],"good":[182],"retrieves":[184],"relevant":[185],"demonstrations,":[186],"helping":[187],"ICL":[189],"model":[190],"generate":[191],"more":[192],"accurate":[193],"stable":[195],"masks.":[197],"Thus,":[198],"introduce":[200],"shape":[202],"stability":[203,210],"score":[204],"(S\u00b3),":[205],"which":[206,249],"evaluates":[207],"morphological":[209],"predicted":[212],"masks":[213],"under":[214],"iterative":[215],"erosion.":[216],"Experiments":[217],"S\u00b3":[219,267],"correlates":[220],"strongly":[221],"with":[222,244,282],"true":[223],"quality":[225],"(Pearson":[226],">":[227],"0.8),":[228],"serving":[229],"reliable":[232],"proxy.":[234],"reduce":[236],"S\u00b3\u2019s":[237],"per-query":[238],"cost,":[239],"parallel":[242],"prediction":[243],"reciprocal":[245,260],"neighbor":[246],"reuse":[247],"(P2R),":[248],"accelerates":[250],"inference":[251],"by":[252],"parallelizing":[253],"encoding":[254],"reusing":[256],"selections":[258],"across":[259,274],"neighbors,":[261],"avoiding":[262],"redundant":[263],"computation.":[264],"Built":[265],"P2R,":[269],"improves":[271],"ICLM":[272],"FUNDUS,":[275],"Brain":[276],"MRI,":[277],"Chest":[279],"X-ray":[280],"datasets,":[281],"up":[283],"10.6%":[285],"gain":[286],"fundus":[288],"segmentation.":[289]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}