{"id":"https://openalex.org/W4415194021","doi":"https://doi.org/10.1109/iccvw69036.2025.11495570","title":"VFM-UDA++: Improving Network Architectures and Data Strategies for Unsupervised Domain Adaptive Semantic Segmentation","display_name":"VFM-UDA++: Improving Network Architectures and Data Strategies for Unsupervised Domain Adaptive Semantic Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415194021","doi":"https://doi.org/10.1109/iccvw69036.2025.11495570"},"language":"en","primary_location":{"id":"doi:10.1109/iccvw69036.2025.11495570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.11495570","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 Workshops (ICCVW)","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/2503.10685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072606911","display_name":"Brun\u00f3 B. Englert","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Brun\u00f3 B. Englert","raw_affiliation_strings":["Eindhoven University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024010116","display_name":"Gijs Dubbelman","orcid":"https://orcid.org/0000-0001-6635-3245"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Gijs Dubbelman","raw_affiliation_strings":["Eindhoven University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology","institution_ids":["https://openalex.org/I83019370"]}]}],"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":0.31717031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7745","last_page":"7755"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9340999722480774,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9340999722480774,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9018999934196472,"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/leverage","display_name":"Leverage (statistics)","score":0.7128000259399414},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5550000071525574},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5475000143051147},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47290000319480896},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4652000069618225},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46299999952316284},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45680001378059387},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42879998683929443},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40369999408721924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044000267982483},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7128000259399414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5860999822616577},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5550000071525574},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5475000143051147},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5271000266075134},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4652000069618225},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39660000801086426},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26429998874664307}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccvw69036.2025.11495570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.11495570","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 Workshops (ICCVW)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.10685","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10685","pdf_url":"https://arxiv.org/pdf/2503.10685","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2503.10685","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10685","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.10685","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10685","pdf_url":"https://arxiv.org/pdf/2503.10685","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[{"id":"https://openalex.org/G6801139879","display_name":"Edge AI Technologies for Optimised Performance Embedded Processing","funder_award_id":"101097300","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"Domain":[1],"Adaptation":[2],"(UDA)":[3],"enables":[4],"strong":[5],"generalization":[6],"from":[7,129,188],"a":[8,57,62,172],"labeled":[9],"source":[10,132],"domain":[11],"to":[12,43,80,93,117,186],"an":[13],"unlabeled":[14],"target":[15,135],"domain,":[16],"often":[17],"with":[18,61,120,163],"limited":[19],"data.":[20,136],"In":[21],"parallel,":[22],"Vision":[23],"Foundation":[24],"Models":[25],"(VFMs)":[26],"pretrained":[27],"at":[28],"scale":[29,162],"without":[30],"labels":[31],"have":[32],"also":[33,68],"shown":[34],"impressive":[35],"downstream":[36],"performance":[37,77,144],"and":[38,123,133,170],"generalization.":[39,65],"This":[40],"motivates":[41],"us":[42],"explore":[44],"how":[45,126],"UDA":[46,127,158,184],"can":[47,142],"best":[48],"leverage":[49],"VFMs.":[50,81],"Prior":[51],"work":[52],"(VFM-UDA)":[53],"demonstrated":[54],"that":[55,70,182],"replacing":[56],"standard":[58,147],"ImageNet-pretrained":[59],"encoder":[60],"VFM":[63],"improves":[64],"However,":[66],"it":[67],"showed":[69],"commonly":[71],"used":[72],"feature":[73,114],"distance":[74,115],"losses":[75],"harm":[76],"when":[78,177],"applied":[79],"Additionally,":[82],"VFM-UDA":[83],"does":[84],"not":[85,161],"incorporate":[86],"multi-scale":[87,110],"inductive":[88],"biases,":[89],"which":[90,104],"are":[91],"known":[92],"improve":[94,143],"semantic":[95],"segmentation.":[96],"Building":[97],"on":[98,145],"these":[99,139],"insights,":[100],"we":[101,141],"propose":[102],"VFM-UDA++,":[103],"(1)":[105],"investigates":[106],"the":[107,146,179],"role":[108],"of":[109],"features,":[111],"(2)":[112],"adapts":[113],"loss":[116],"be":[118],"compatible":[119],"ViT-based":[121],"VFMs":[122],"(3)":[124],"evaluates":[125],"benefits":[128],"increased":[130,189],"synthetic":[131],"real":[134],"By":[137],"addressing":[138],"questions,":[140],"GTA5":[148],"$\\rightarrow$":[149],"Cityscapes":[150],"benchmark":[151],"by":[152],"+1.4":[153],"mIoU.":[154],"While":[155],"prior":[156],"non-VFM":[157],"methods":[159],"did":[160],"more":[164],"data,":[165,180],"VFM-UDA++":[166],"shows":[167],"consistent":[168],"improvement":[169],"achieves":[171],"further":[173],"+2.4":[174],"mIoU":[175],"gain":[176],"scaling":[178],"demonstrating":[181],"VFM-based":[183],"continues":[185],"benefit":[187],"data":[190],"availability.":[191]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-15T00:00:00"}