{"id":"https://openalex.org/W4417290382","doi":"https://doi.org/10.1109/wacv61042.2026.00176","title":"From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation","display_name":"From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417290382","doi":"https://doi.org/10.1109/wacv61042.2026.00176"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00176","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.09307","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059248402","display_name":"Shantanu Agnihotri","orcid":null},"institutions":[{"id":"https://openalex.org/I83205935","display_name":"Malaviya National Institute of Technology Jaipur","ror":"https://ror.org/0077k1j32","country_code":"IN","type":"education","lineage":["https://openalex.org/I83205935"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shivanshu Agnihotri","raw_affiliation_strings":["Malaviya National Institute of Technology,Jaipur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Malaviya National Institute of Technology,Jaipur,India","institution_ids":["https://openalex.org/I83205935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015650149","display_name":"Snehashis Majhi","orcid":"https://orcid.org/0000-0002-9101-017X"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Snehashis Majhi","raw_affiliation_strings":["Côte d’Azur University,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Côte d’Azur University,France","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113405400","display_name":"Deepak Ranjan Nayak","orcid":null},"institutions":[{"id":"https://openalex.org/I83205935","display_name":"Malaviya National Institute of Technology Jaipur","ror":"https://ror.org/0077k1j32","country_code":"IN","type":"education","lineage":["https://openalex.org/I83205935"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Deepak Ranjan Nayak","raw_affiliation_strings":["Malaviya National Institute of Technology,Jaipur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Malaviya National Institute of Technology,Jaipur,India","institution_ids":["https://openalex.org/I83205935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044673103","display_name":"Debesh Jha","orcid":"https://orcid.org/0000-0002-8078-6730"},"institutions":[{"id":"https://openalex.org/I189957204","display_name":"University of South Dakota","ror":"https://ror.org/0043h8f16","country_code":"US","type":"education","lineage":["https://openalex.org/I189957204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debesh Jha","raw_affiliation_strings":["University of South Dakota,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Dakota,USA","institution_ids":["https://openalex.org/I189957204"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00513196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1757","last_page":"1766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.9452999830245972,"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":0.9452999830245972,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.01549999974668026,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.013100000098347664,"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/segmentation","display_name":"Segmentation","score":0.6514999866485596},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6367999911308289},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5845999717712402},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5580000281333923},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.48249998688697815},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.42590001225471497},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.40389999747276306},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.38370001316070557},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.358599990606308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476999759674072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6780999898910522},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6514999866485596},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6367999911308289},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5580000281333923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5138000249862671},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.48249998688697815},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.42590001225471497},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3571999967098236},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28850001096725464},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2599000036716461}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00176","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:2512.09307","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.09307","pdf_url":"https://arxiv.org/pdf/2512.09307","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.2512.09307","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.09307","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:2512.09307","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.09307","pdf_url":"https://arxiv.org/pdf/2512.09307","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":[{"id":"https://openalex.org/F4320306227","display_name":"Arthritis National Research Foundation","ror":"https://ror.org/03abbex33"},{"id":"https://openalex.org/F4320312774","display_name":"University of South Dakota","ror":"https://ror.org/0043h8f16"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417290382.pdf","grobid_xml":"https://content.openalex.org/works/W4417290382.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"polyp":[1,98],"segmentation":[2,64,137],"during":[3],"colonoscopy":[4],"is":[5,100,216],"critical":[6],"for":[7,171],"the":[8,27,58,106,129,154,205],"early":[9],"detection":[10],"of":[11,30,46,108,113,132],"colorectal":[12],"cancer":[13],"and":[14,23,26,40,49,77,111,141,163,165,192],"still":[15],"remains":[16],"challenging":[17],"due":[18,104],"to":[19,55,62,92,105],"significant":[20],"size,":[21],"shape,":[22],"color":[24],"variations,":[25],"camouflaged":[28],"nature":[29],"polyps.":[31],"While":[32],"lightweight":[33,136],"baseline":[34,199],"models":[35,71,134,156,200],"such":[36,72,160,186],"as":[37,73,161,187,202,204],"U-Net,":[38],"U-Net++,":[39],"PraNet":[41],"offer":[42],"advantages":[43],"in":[44,144],"terms":[45],"easy":[47],"deployment":[48,143],"low":[50],"computational":[51],"cost,":[52],"they":[53],"struggle":[54],"deal":[56],"with":[57,208],"above":[59],"issues,":[60],"leading":[61],"limited":[63],"performance.":[65],"In":[66,147],"contrast,":[67],"large-scale":[68,109],"vision":[69],"foundation":[70,133,155],"SAM,":[74],"DINOv2,":[75],"OneFormer,":[76],"Mask2Former":[78],"have":[79],"exhibited":[80],"impressive":[81],"generalization":[82,176],"performance":[83],"across":[84,182],"natural":[85],"image":[86],"domains.":[87],"However,":[88],"their":[89,175],"direct":[90],"transfer":[91],"medical":[93],"imaging":[94],"tasks":[95],"(e.g.,":[96],"colonoscopic":[97],"segmentation)":[99],"not":[101],"straightforward,":[102],"primarily":[103],"scarcity":[107],"datasets":[110],"lack":[112],"domain-specific":[114],"knowledge.":[115],"To":[116],"bridge":[117],"this":[118],"gap,":[119],"we":[120,149],"propose":[121],"a":[122],"novel":[123],"distillation":[124],"framework,":[125],"PolypDiFoM,":[126],"that":[127],"transfers":[128],"rich":[130],"representations":[131],"into":[135,157],"baselines,":[138],"allowing":[139],"efficient":[140],"accurate":[142],"clinical":[145],"settings.":[146],"particular,":[148],"infuse":[150],"semantic":[151],"priors":[152],"from":[153],"canonical":[158],"architectures":[159],"U-Net":[162],"U-Net++":[164],"further":[166],"perform":[167],"frequency":[168],"domain":[169],"encoding":[170],"enhanced":[172],"distillation,":[173],"corroborating":[174],"capability.":[177],"Extensive":[178],"experiments":[179],"are":[180],"performed":[181],"five":[183],"benchmark":[184],"datasets,":[185],"Kvasir-SEG,":[188],"CVC-ClinicDB,":[189],"ETIS,":[190],"ColonDB,":[191],"CVC-300.":[193],"Notably,":[194],"PolypDiFoM":[195],"consistently":[196],"outperforms":[197],"respective":[198],"significantly,":[201],"well":[203],"state-of-the-art":[206],"model,":[207],"nearly":[209],"9\u00d7":[210],"reduced":[211],"computation":[212],"overhead.":[213],"The":[214],"code":[215],"available":[217],"at":[218],"GitHub":[219],"repository.":[220]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-12-12T00:00:00"}