{"id":"https://openalex.org/W7140047993","doi":"https://doi.org/10.1134/s1064562425700541","title":"Where Semantics Meets Space: A Layer-Wise Analysis of Frozen Encoders for Efficient Polyp Segmentation","display_name":"Where Semantics Meets Space: A Layer-Wise Analysis of Frozen Encoders for Efficient Polyp Segmentation","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7140047993","doi":"https://doi.org/10.1134/s1064562425700541"},"language":"en","primary_location":{"id":"doi:10.1134/s1064562425700541","doi":"https://doi.org/10.1134/s1064562425700541","is_oa":false,"landing_page_url":"https://doi.org/10.1134/s1064562425700541","pdf_url":null,"source":{"id":"https://openalex.org/S19800340","display_name":"Doklady Mathematics","issn_l":"1064-5624","issn":["1064-5624","1531-8362"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["dongbi-c","jufo-1","norway-1","poland-40","russia-white-list-2"],"host_organization":"https://openalex.org/P4310320267","host_organization_name":"Pleiades Publishing","host_organization_lineage":["https://openalex.org/P4310320267","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Pleiades Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Doklady Mathematics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102717023","display_name":"A. T. M. Taha","orcid":"https://orcid.org/0009-0006-6346-4162","observed_orcids":["https://orcid.org/0009-0006-6346-4162"]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"A. Taha","raw_affiliation_strings":["Innopolis University, 420500, Innopolis, Russia","Research Center for Artificial Intelligence, Innopolis University, 420500, Innopolis, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innopolis University, 420500, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]},{"raw_affiliation_string":"Research Center for Artificial Intelligence, Innopolis University, 420500, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079013160","display_name":"Rustam Lukmanov","orcid":"https://orcid.org/0000-0001-9257-7410","observed_orcids":["https://orcid.org/0000-0001-9257-7410"]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"R. Lukmanov","raw_affiliation_strings":["Innopolis University, 420500, Innopolis, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innopolis University, 420500, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5079013160","https://openalex.org/A5102717023"],"corresponding_institution_ids":["https://openalex.org/I4210116741"],"apc_list":null,"apc_paid":null,"fwci":0.3685,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51965674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"112","issue":"3","first_page":"592","last_page":"599"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.6449999809265137,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.6449999809265137,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.13619999587535858,"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":0.10570000112056732,"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/polyp-segmentation","display_name":"polyp segmentation","score":0.9459999799728394},{"id":"https://openalex.org/keywords/frozen-encoder","display_name":"frozen encoder","score":0.7429999709129333},{"id":"https://openalex.org/keywords/foundation-models","display_name":"foundation models","score":0.7440000176429749},{"id":"https://openalex.org/keywords/layer-by-layer-analysis","display_name":"layer-wise analysis","score":0.7649999856948853},{"id":"https://openalex.org/keywords/endoscopic-image-segmentation","display_name":"endoscopic image segmentation","score":0.7419999837875366},{"id":"https://openalex.org/keywords/clinical-ai","display_name":"clinical AI","score":0.546999990940094}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7511000037193298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203999757766724},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6650000214576721},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.6462000012397766},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6065000295639038},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6053000092506409},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5467000007629395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517300009727478},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C2909374376","wikidata":"https://www.wikidata.org/wiki/Q2726733","display_name":"Nanodevice","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34689998626708984},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3407999873161316},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2709999978542328},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.25369998812675476},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1134/s1064562425700541","doi":"https://doi.org/10.1134/s1064562425700541","is_oa":false,"landing_page_url":"https://doi.org/10.1134/s1064562425700541","pdf_url":null,"source":{"id":"https://openalex.org/S19800340","display_name":"Doklady Mathematics","issn_l":"1064-5624","issn":["1064-5624","1531-8362"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["dongbi-c","jufo-1","norway-1","poland-40","russia-white-list-2"],"host_organization":"https://openalex.org/P4310320267","host_organization_name":"Pleiades Publishing","host_organization_lineage":["https://openalex.org/P4310320267","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Pleiades Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Doklady Mathematics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2008359794","https://openalex.org/W2108598243","https://openalex.org/W2432481613","https://openalex.org/W2884436604","https://openalex.org/W2963351448","https://openalex.org/W2988299447","https://openalex.org/W3092344722","https://openalex.org/W3127751679","https://openalex.org/W3208967909","https://openalex.org/W4287225564","https://openalex.org/W4319298404","https://openalex.org/W4319300502","https://openalex.org/W4321328679","https://openalex.org/W4363650233","https://openalex.org/W4382877880","https://openalex.org/W4392452991","https://openalex.org/W4399849668","https://openalex.org/W4402727326","https://openalex.org/W4405278863","https://openalex.org/W4406316501","https://openalex.org/W4409983468","https://openalex.org/W4412623472"],"related_works":["https://openalex.org/W4417491413","https://openalex.org/W4386362742","https://openalex.org/W4415960702","https://openalex.org/W7214545288","https://openalex.org/W4405865138","https://openalex.org/W7214184950","https://openalex.org/W3173745881","https://openalex.org/W7168169361","https://openalex.org/W7201846024","https://openalex.org/W7220995932"],"abstract_inverted_index":{"Abstract":[0],"While":[1],"deep":[2],"encoder-decoder":[3],"models":[4],"dominate":[5],"endoscopic":[6],"segmentation,":[7],"their":[8],"reliance":[9],"on":[10,113],"full":[11],"fine-tuning":[12],"or":[13],"training":[14,104],"from":[15],"scratch":[16],"is":[17,47],"computationally":[18],"expensive":[19],"and":[20,95,139],"data-intensive.":[21],"This":[22,125],"paper":[23],"challenges":[24],"this":[25],"by":[26],"demonstrating":[27],"that":[28],"an":[29,82,88,128],"extremely":[30],"efficient":[31,132],"model\u2014a":[32],"frozen":[33],"foundation":[34],"model":[35],"encoder":[36],"with":[37,87,119],"a":[38,48,77,120],"shallow":[39],"decoder\u2014can":[40],"achieve":[41],"state-of-the-art":[42],"performance.":[43],"Our":[44],"core":[45],"contribution":[46],"systematic,":[49],"layer-wise":[50],"analysis":[51],"to":[52],"identify":[53,76],"the":[54,61,65,70,96,114,137],"single":[55],"most":[56,72],"effective":[57],"feature":[58,133],"source":[59],"within":[60],"encoder\u2019s":[62],"hierarchy,":[63],"challenging":[64,115],"common":[66],"practice":[67],"of":[68,123],"using":[69],"final,":[71],"abstract":[73],"layer.":[74],"We":[75],"distinct":[78],"performance":[79],"peak":[80],"at":[81],"intermediate":[83],"layer":[84],"(Layer":[85],"12),":[86],"optimal":[89],"trade-off":[90],"between":[91],"high-level":[92],"semantic":[93],"understanding":[94],"high-resolution":[97],"spatial":[98],"fidelity":[99],"crucial":[100],"for":[101,131,142],"segmentation.":[102],"Despite":[103],"only":[105],"650k":[106],"parameters,":[107],"our":[108],"method":[109],"surpasses":[110],"existing":[111],"benchmarks":[112],"multi-center":[116],"PolypGen":[117],"dataset":[118],"Dice":[121],"score":[122],"0.972.":[124],"work":[126],"provides":[127],"evidence-based":[129],"methodology":[130],"extraction,":[134],"significantly":[135],"lowering":[136],"computational":[138],"data":[140],"barriers":[141],"developing":[143],"high-performance":[144],"clinical":[145],"AI":[146],"tools.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-03-23T00:00:00"}