{"id":"https://openalex.org/W7165917002","doi":"https://doi.org/10.48550/arxiv.2606.25278","title":"Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation","display_name":"Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation","publication_year":2026,"publication_date":"2026-06-24","ids":{"openalex":"https://openalex.org/W7165917002","doi":"https://doi.org/10.48550/arxiv.2606.25278"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.25278","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25278","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.2606.25278","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090578536","display_name":"X . Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xiaopei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062441362","display_name":"Yuenan Hou","orcid":"https://orcid.org/0000-0002-2844-7416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Yuenan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101494816","display_name":"Junkai Xu","orcid":"https://orcid.org/0000-0002-6366-8863"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Junkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139385778","display_name":"Wenxiao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenxiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139371851","display_name":"Binbin Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Binbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139371592","display_name":"Yu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139328967","display_name":"Ping Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139331495","display_name":"Haifeng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Haifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139379163","display_name":"Deng Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139354963","display_name":"Wanli Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Wanli","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/T10036","display_name":"Advanced Neural Network Applications","score":0.8151999711990356,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8151999711990356,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.02370000071823597,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.017999999225139618,"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/snapshot","display_name":"Snapshot (computer storage)","score":0.8174999952316284},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.707099974155426},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6535999774932861},{"id":"https://openalex.org/keywords/adept","display_name":"Adept","score":0.5954999923706055},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.4316999912261963},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.35659998655319214},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3328000009059906},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3296000063419342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8320000171661377},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.8174999952316284},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.707099974155426},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6535999774932861},{"id":"https://openalex.org/C2776904630","wikidata":"https://www.wikidata.org/wiki/Q356336","display_name":"Adept","level":3,"score":0.5954999923706055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5812000036239624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5637999773025513},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.25278","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25278","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.2606.25278","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25278","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":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.573447048664093}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-modal":[0],"fusion":[1],"and":[2,57,59,192,204,217],"multi-model":[3],"ensembling":[4,132],"are":[5],"prevalent":[6],"in":[7,182],"enhancing":[8],"the":[9,16,36,47,51,64,79,83,87,92,102,113,116,121,124,135,149,156,165,180,183],"performance":[10,38,114],"of":[11,115,123,138],"3D":[12,214],"semantic":[13],"segmentation.":[14],"Despite":[15],"impressive":[17],"performance,":[18],"these":[19],"methods":[20],"either":[21],"rely":[22],"on":[23,202],"auxiliary":[24],"input":[25],"signals":[26],"or":[27],"suffer":[28],"from":[29,50,86,101],"costly":[30],"computational":[31],"expense.":[32],"To":[33],"efficaciously":[34],"enhance":[35],"segmentation":[37,215],"without":[39,221],"introducing":[40,222],"intolerable":[41],"costs,":[42],"we":[43,71,141],"propose":[44,142],"to":[45,63,77,97,129,179],"transfer":[46],"rich":[48],"knowledge":[49,68,85],"multi-modal":[52,88,107,117],"model":[53,61,81,131,152,169],"(i.e.,":[54],"point":[55],"clouds":[56],"images)":[58],"multiple":[60,160],"experts":[62],"point-cloudbased":[65],"network":[66],"through":[67],"distillation.":[69],"Specifically,":[70],"present":[72],"Information-oriented":[73],"Heterogeneous":[74,191],"Distillation":[75,145],"(IHD)":[76],"help":[78],"uni-modal":[80],"absorb":[82],"complementary":[84],"teacher.":[89],"We":[90],"design":[91],"Information-Oriented":[93],"Filtering":[94],"(IOF)":[95],"strategy":[96],"select":[98],"informative":[99],"images":[100],"continuous":[103],"image":[104],"sequence":[105],"for":[106,168],"fusion.":[108],"This":[109],"practice":[110],"can":[111,208],"boost":[112],"teacher,":[118,174],"thus":[119],"benefiting":[120],"learning":[122],"student.":[125],"Besides,":[126],"as":[127,159],"opposed":[128],"vanilla":[130],"that":[133],"requires":[134],"separate":[136],"training":[137,157,166],"each":[139,172],"expert,":[140],"Adept":[143,193],"Snapshot":[144,194],"(ASD).":[146],"ASD":[147],"treats":[148],"freely":[150],"available":[151,232],"snapshots":[153],"generated":[154],"during":[155],"phase":[158],"experts,":[161],"which":[162],"significantly":[163],"reduces":[164],"cost":[167],"ensembling.":[170],"For":[171],"expert":[173],"it":[175,186],"only":[176],"provides":[177],"supervision":[178],"student":[181],"class":[184],"where":[185],"is":[187],"adept.":[188],"The":[189,226],"resulting":[190],"Knowledge":[195],"Distillation,":[196],"dubbed":[197],"HAS-KD,":[198],"attains":[199],"state-of-the-art":[200],"results":[201],"ScanNetV2":[203],"S3DIS":[205],"datasets.":[206],"HAS-KD":[207],"be":[209,229],"seamlessly":[210],"integrated":[211],"into":[212],"contemporary":[213],"algorithms":[216],"bring":[218],"considerable":[219],"gains":[220],"extra":[223],"inference":[224],"burdens.":[225],"code":[227],"will":[228],"made":[230],"publicly":[231],"upon":[233],"publication.":[234]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-26T00:00:00"}