{"id":"https://openalex.org/W7140134381","doi":"https://doi.org/10.48550/arxiv.2603.19757","title":"Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation","display_name":"Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7140134381","doi":"https://doi.org/10.48550/arxiv.2603.19757"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.19757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19757","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":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.2603.19757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130350552","display_name":"Yifei Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yifei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130377600","display_name":"Fanyu Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Fanyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101658474","display_name":"Yinsheng Li","orcid":"https://orcid.org/0000-0002-1635-5178"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yinsheng","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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8014000058174133,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.8014000058174133,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.0625,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.013899999670684338,"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/inference","display_name":"Inference","score":0.6958000063896179},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6790000200271606},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6523000001907349},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6389999985694885},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5058000087738037},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48410001397132874},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4596000015735626},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.43220001459121704},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4284999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230000138282776},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6958000063896179},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6790000200271606},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6523000001907349},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6389999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5314000248908997},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5241000056266785},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4284999966621399},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4253999888896942},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.35359999537467957},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.19757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19757","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":"doi:10.48550/arxiv.2603.19757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19757","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Few-shot":[0],"3D":[1,84],"semantic":[2,8],"segmentation":[3],"aims":[4],"to":[5,34,44,75],"generate":[6],"accurate":[7],"masks":[9],"for":[10,82],"query":[11,36,113],"point":[12],"clouds":[13],"with":[14],"only":[15],"a":[16,71,95,121],"few":[17],"annotated":[18],"support":[19,32,111],"examples.":[20],"Existing":[21],"prototype-based":[22],"methods":[23],"typically":[24],"construct":[25],"compact":[26],"and":[27,59,112,140,151],"deterministic":[28],"prototypes":[29,127],"from":[30,109],"the":[31,46,147],"set":[33],"guide":[35],"segmentation.":[37,85],"However,":[38],"such":[39],"rigid":[40],"representations":[41,103],"are":[42],"unable":[43],"capture":[45],"intrinsic":[47],"uncertainty":[48,77,136,168],"introduced":[49],"by":[50,104],"scarce":[51],"supervision,":[52],"which":[53],"often":[54],"results":[55],"in":[56],"degraded":[57],"robustness":[58],"limited":[60,107],"generalization.":[61],"In":[62],"this":[63],"work,":[64],"we":[65,116],"propose":[66],"UPL":[67,93,157],"(Uncertainty-aware":[68],"Prototype":[69],"Learning),":[70],"probabilistic":[72,132],"approach":[73],"designed":[74],"incorporate":[76],"modeling":[78],"into":[79],"prototype":[80,97,102,118],"learning":[81,119],"few-shot":[83],"Our":[86],"framework":[87],"introduces":[88,94],"two":[89],"key":[90],"components.":[91],"First,":[92],"dual-stream":[96],"refinement":[98],"module":[99],"that":[100,155],"enriches":[101],"jointly":[105],"leveraging":[106],"information":[108],"both":[110],"samples.":[114],"Second,":[115],"formulate":[117],"as":[120,128],"variational":[122],"inference":[123],"problem,":[124],"regarding":[125],"class":[126],"latent":[129],"variables.":[130],"This":[131],"formulation":[133],"enables":[134],"explicit":[135],"modeling,":[137],"providing":[138,166],"robust":[139],"interpretable":[141],"mask":[142],"predictions.":[143],"Extensive":[144],"experiments":[145],"on":[146],"widely":[148],"used":[149],"ScanNet":[150],"S3DIS":[152],"benchmarks":[153],"show":[154],"our":[156],"achieves":[158],"consistent":[159],"state-of-the-art":[160],"performance":[161],"under":[162],"different":[163],"settings":[164],"while":[165],"reliable":[167],"estimation.":[169],"The":[170],"code":[171],"is":[172],"available":[173],"at":[174],"https://fdueblab-upl.github.io/.":[175]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-24T00:00:00"}