{"id":"https://openalex.org/W4402980248","doi":"https://doi.org/10.1109/icme57554.2024.10687769","title":"ELiTe: Efficient Image-to-LiDAR Knowledge Transfer for Semantic Segmentation","display_name":"ELiTe: Efficient Image-to-LiDAR Knowledge Transfer for Semantic Segmentation","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980248","doi":"https://doi.org/10.1109/icme57554.2024.10687769"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687769","doi":"https://doi.org/10.1109/icme57554.2024.10687769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687769","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.04121","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017329987","display_name":"Zhibo Zhang","orcid":"https://orcid.org/0000-0001-8830-3935","observed_orcids":["https://orcid.org/0000-0001-8830-3935"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibo Zhang","raw_affiliation_strings":["Fudan University,School of Computer Science,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ximing Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ximing Yang","raw_affiliation_strings":["Fudan University,School of Computer Science,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693733","display_name":"Weizhong Zhang","orcid":"https://orcid.org/0000-0001-7311-0698","observed_orcids":["https://orcid.org/0000-0001-7311-0698","https://orcid.org/0000-0003-2164-6321"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhong Zhang","raw_affiliation_strings":["Fudan University,School of Data Science,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Data Science,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113456828","display_name":"Cheng Jin","orcid":"https://orcid.org/0009-0004-1111-2451","observed_orcids":["https://orcid.org/0009-0004-1111-2451"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Jin","raw_affiliation_strings":["Fudan University,School of Computer Science,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.8235,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79629179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7143999934196472,"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":0.7143999934196472,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.25679999589920044,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.014399999752640724,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cross-modal-knowledge-distillation","display_name":"cross-modal knowledge distillation","score":0.8360000252723694},{"id":"https://openalex.org/keywords/lidar-semantic-segmentation","display_name":"LiDAR semantic segmentation","score":0.9160000085830688},{"id":"https://openalex.org/keywords/point-cloud-representation-learning","display_name":"point cloud representation learning","score":0.9390000104904175},{"id":"https://openalex.org/keywords/vision-foundation-models","display_name":"vision foundation models","score":0.7730000019073486},{"id":"https://openalex.org/keywords/pseudo-label-generation","display_name":"pseudo-label generation","score":0.7310000061988831},{"id":"https://openalex.org/keywords/segment-anything-model","display_name":"Segment Anything Model","score":0.996999979019165},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.8519999980926514},{"id":"https://openalex.org/keywords/semantickitti","display_name":"SemanticKITTI","score":0.628000020980835},{"id":"https://openalex.org/keywords/lightweight-student-models","display_name":"lightweight student models","score":0.6110000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6378865838050842},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.6017066836357117},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5686434507369995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5476306080818176},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5454585552215576},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.47914665937423706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4493348300457001},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.2059425413608551},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.18941855430603027},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.1578064262866974}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icme57554.2024.10687769","doi":"https://doi.org/10.1109/icme57554.2024.10687769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687769","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.04121","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.04121","pdf_url":"https://arxiv.org/pdf/2405.04121","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,"listed_in":[],"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":"pmh:oai:repository.hkust.edu.hk:1783.1-159316","doi":null,"is_oa":false,"landing_page_url":"http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001364925201103","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"doi:10.48550/arxiv.2405.04121","doi":"https://doi.org/10.48550/arxiv.2405.04121","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.04121","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.04121","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.04121","pdf_url":"https://arxiv.org/pdf/2405.04121","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402980248.pdf","grobid_xml":"https://content.openalex.org/works/W4402980248.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2150066425","https://openalex.org/W2626778328","https://openalex.org/W2965803762","https://openalex.org/W2990479855","https://openalex.org/W3003437478","https://openalex.org/W3035275207","https://openalex.org/W3109154950","https://openalex.org/W3137210930","https://openalex.org/W3160425077","https://openalex.org/W3173732446","https://openalex.org/W3177330511","https://openalex.org/W3181190968","https://openalex.org/W3198675127","https://openalex.org/W3206480303","https://openalex.org/W3206724875","https://openalex.org/W4200635407","https://openalex.org/W4226253852","https://openalex.org/W4304092252","https://openalex.org/W4312367717","https://openalex.org/W4312419284","https://openalex.org/W4382240089","https://openalex.org/W4385570973","https://openalex.org/W4386160292","https://openalex.org/W4390874575","https://openalex.org/W4391930719"],"related_works":["https://openalex.org/W4390874225","https://openalex.org/W7153050025","https://openalex.org/W4400488050","https://openalex.org/W4401990915","https://openalex.org/W7125124696","https://openalex.org/W4414940734","https://openalex.org/W4386160130","https://openalex.org/W4312419284","https://openalex.org/W7214557932","https://openalex.org/W4406457674"],"abstract_inverted_index":{"Cross-modal":[0],"knowledge":[1,54,70,117],"transfer":[2,71,118],"enhances":[3],"point":[4],"cloud":[5],"representation":[6],"learning":[7],"in":[8,119],"LiDAR":[9],"semantic":[10,114],"segmentation.":[11],"Despite":[12],"its":[13,141],"potential,":[14],"the":[15,39,56,85,99,125],"weak":[16],"teacher":[17,87],"challenge":[18],"arises":[19],"due":[20],"to":[21,72,83,107],"repetitive":[22],"and":[23,28,88,143],"non-diverse":[24],"car":[25],"camera":[26],"images":[27],"sparse,":[29],"inaccurate":[30],"ground":[31],"truth":[32],"labels.":[33],"To":[34],"address":[35],"this,":[36],"we":[37,97],"propose":[38],"Efficient":[40,116],"Image-to-LiDAR":[41],"Knowledge":[42,50],"Transfer":[43],"(ELiTe)":[44],"paradigm.":[45],"ELiTe":[46,79,120],"introduces":[47],"Patch-to-Point":[48],"Multi-Stage":[49],"Distillation,":[51],"transferring":[52],"comprehensive":[53],"from":[55],"Vision":[57],"Foundation":[58],"Model":[59,102],"(VFM),":[60],"extensively":[61],"trained":[62],"on":[63,124],"diverse":[64],"open-world":[65],"images.":[66],"This":[67],"enables":[68],"effective":[69],"a":[73],"lightweight":[74],"student":[75],"model":[76,91],"across":[77],"modalities.":[78],"employs":[80],"Parameter-Efficient":[81],"Fine-Tuning":[82],"strengthen":[84],"VFM":[86],"expedite":[89],"large-scale":[90],"training":[92],"with":[93,136],"minimal":[94],"costs.":[95],"Additionally,":[96],"introduce":[98],"Segment":[100],"Anything":[101],"based":[103],"Pseudo-Label":[104],"Generation":[105],"approach":[106,133],"enhance":[108],"low-quality":[109],"image":[110],"labels,":[111],"facilitating":[112],"robust":[113],"representations.":[115],"yields":[121],"state-of-the-art":[122],"results":[123],"SemanticKITTI":[126],"benchmark,":[127],"outperforming":[128],"real-time":[129],"inference":[130],"models.":[131],"Our":[132],"achieves":[134],"this":[135],"significantly":[137],"fewer":[138],"parameters,":[139],"confirming":[140],"effectiveness":[142],"efficiency.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2024-10-01T00:00:00"}