{"id":"https://openalex.org/W7138874431","doi":"https://doi.org/10.48550/arxiv.2603.16083","title":"Structured prototype regularization for synthetic-to-real driving scene parsing","display_name":"Structured prototype regularization for synthetic-to-real driving scene parsing","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7138874431","doi":"https://doi.org/10.48550/arxiv.2603.16083"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.16083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16083","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.16083","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017685857","display_name":"Jiahe Fan","orcid":"https://orcid.org/0000-0002-2364-6811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Jiahe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130198239","display_name":"Xiao Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070534945","display_name":"Sergey Vityazev","orcid":"https://orcid.org/0000-0002-9851-5066"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vityazev, Sergey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129959497","display_name":"George Giakos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giakos, George","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068080569","display_name":"Shaolong Shu","orcid":"https://orcid.org/0000-0001-7343-1782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shu, Shaolong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129848582","display_name":"Rui Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5572999715805054,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5572999715805054,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.12770000100135803,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.12150000035762787,"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/parsing","display_name":"Parsing","score":0.7882999777793884},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5662000179290771},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5436999797821045},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.49790000915527344},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4625000059604645},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4296000003814697},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.41830000281333923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40720000863075256},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4059000015258789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252000212669373},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7882999777793884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6762999892234802},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5662000179290771},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.49790000915527344},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40149998664855957},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.35359999537467957},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3508000075817108},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.16083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16083","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.16083","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16083","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7369899749755859}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Driving":[0],"scene":[1,123,203],"parsing":[2,124,204],"is":[3],"critical":[4],"for":[5,197],"autonomous":[6],"vehicles":[7],"to":[8,46,50,98,119],"operate":[9],"reliably":[10],"in":[11,62,126,201],"complex":[12],"real-world":[13,47,127],"traffic":[14],"environments.":[15],"To":[16,100],"reduce":[17],"the":[18,51,56,77,81,95,130,145,159,180,191],"reliance":[19],"on":[20,38,71,175],"costly":[21],"pixel-level":[22,166],"annotations,":[23],"synthetic":[24,39],"datasets":[25],"with":[26],"automatically":[27],"generated":[28],"labels":[29],"have":[30],"become":[31],"a":[32,85,107,165],"popular":[33],"alternative.":[34],"However,":[35],"models":[36],"trained":[37],"data":[40],"often":[41],"perform":[42],"poorly":[43],"when":[44],"applied":[45],"scenes":[48],"due":[49],"synthetic-to-real":[52,199],"domain":[53,60,110],"gap.":[54],"Despite":[55],"success":[57],"of":[58,80,150,161,193],"unsupervised":[59,109],"adaptation":[61,111,200],"narrowing":[63],"this":[64,104],"gap,":[65],"most":[66],"existing":[67],"methods":[68],"mainly":[69],"focus":[70],"global":[72],"feature":[73,82,117,151,171],"alignment":[74],"while":[75,164],"overlooking":[76],"semantic":[78,87,116,195],"structure":[79,196],"space.":[83],"As":[84],"result,":[86],"relations":[88],"among":[89],"classes":[90],"are":[91],"insufficiently":[92],"modeled,":[93],"limiting":[94],"model's":[96],"ability":[97],"generalize.":[99],"address":[101],"these":[102],"challenges,":[103],"study":[105],"introduces":[106],"novel":[108],"framework":[112],"that":[113,179],"explicitly":[114],"regularizes":[115],"structures":[118],"significantly":[120],"enhance":[121],"driving":[122,202],"performance":[125],"scenarios.":[128],"Specifically,":[129],"proposed":[131,181],"method":[132,182],"enforces":[133],"inter-class":[134],"separation":[135],"and":[136,147],"intra-class":[137],"compactness":[138],"by":[139],"leveraging":[140],"class-specific":[141],"prototypes,":[142],"thereby":[143],"enhancing":[144],"discriminability":[146],"structural":[148],"coherence":[149],"clusters.":[152],"An":[153],"entropy-based":[154],"noise":[155],"filtering":[156],"strategy":[157],"improves":[158],"reliability":[160],"pseudo":[162],"labels,":[163],"attention":[167],"mechanism":[168],"further":[169],"refines":[170],"alignment.":[172],"Extensive":[173],"experiments":[174],"representative":[176],"benchmarks":[177],"demonstrate":[178],"consistently":[183],"outperforms":[184],"recent":[185],"state-of-the-art":[186],"methods.":[187],"These":[188],"results":[189],"underscore":[190],"importance":[192],"preserving":[194],"robust":[198],"tasks.":[205]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-20T00:00:00"}