{"id":"https://openalex.org/W7134805904","doi":"https://doi.org/10.48550/arxiv.2603.07464","title":"Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detection","display_name":"Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detection","publication_year":2026,"publication_date":"2026-03-08","ids":{"openalex":"https://openalex.org/W7134805904","doi":"https://doi.org/10.48550/arxiv.2603.07464"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.07464","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07464","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.2603.07464","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128662953","display_name":"Rui Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128670860","display_name":"Meng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128656519","display_name":"Nanning Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Nanning","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":0.8794999718666077,"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":0.8794999718666077,"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":0.03009999915957451,"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/T10812","display_name":"Human Pose and Action Recognition","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/overfitting","display_name":"Overfitting","score":0.7172999978065491},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7132999897003174},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6294000148773193},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6237999796867371},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5655999779701233},{"id":"https://openalex.org/keywords/lidar","display_name":"Lidar","score":0.5343999862670898},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5195000171661377},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5048999786376953}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7444000244140625},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7172999978065491},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7132999897003174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6948000192642212},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6294000148773193},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6237999796867371},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5655999779701233},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.5343999862670898},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5275999903678894},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5195000171661377},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4016999900341034},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2632000148296356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.07464","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07464","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.2603.07464","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07464","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Monocular":[0],"3D":[1],"object":[2],"detection":[3],"is":[4],"a":[5,82,190],"promising":[6],"yet":[7],"ill-posed":[8],"task":[9],"for":[10,62,195],"autonomous":[11],"vehicles":[12],"due":[13],"to":[14,31,88,117],"the":[15,51,63,69,76,103,110,129,205,208,214],"lack":[16],"of":[17,96,121,157,207],"accurate":[18],"depth":[19,27,97,161],"information.":[20],"Cross-modality":[21],"knowledge":[22],"distillation":[23,61,136],"could":[24],"effectively":[25],"transfer":[26,53,95,105],"information":[28,98],"from":[29,99],"LiDAR":[30,40,100],"image-based":[32,107,124],"network.":[33,108],"However,":[34],"modality":[35,57],"gap":[36,58],"between":[37,123],"image":[38],"and":[39,125,144,155,165,178,189,211],"seriously":[41],"limits":[42],"its":[43],"accuracy.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,113,132,182],"systematically":[49],"investigate":[50],"negative":[52,104],"problem":[54],"induced":[55],"by":[56,159],"in":[59],"cross-modality":[60],"first":[64],"time,":[65],"including":[66],"not":[67],"only":[68],"architecture":[70],"inconsistency":[71],"issue":[72],"but":[73],"more":[74],"importantly":[75],"feature":[77,164],"overfitting":[78],"issue.":[79],"We":[80],"propose":[81],"selective":[83],"learning":[84],"approach":[85,170,202],"named":[86],"MonoSTL":[87],"overcome":[89],"these":[90],"issues,":[91],"which":[92,150],"encourages":[93],"positive":[94,153],"while":[101],"alleviates":[102],"on":[106,187,193],"On":[109,128],"one":[111],"hand,":[112,131],"utilize":[114],"similar":[115],"architectures":[116],"ensure":[118],"spatial":[119],"alignment":[120],"features":[122,154],"LiDAR-based":[126],"networks.":[127],"other":[130],"develop":[133],"two":[134],"novel":[135],"modules,":[137],"namely":[138],"Depth-Aware":[139,145],"Selective":[140,146],"Feature":[141],"Distillation":[142,148],"(DASFD)":[143],"Relation":[147],"(DASRD),":[149],"selectively":[151],"learn":[152],"relationships":[156],"objects":[158],"integrating":[160],"uncertainty":[162],"into":[163,175],"relation":[166],"distillations,":[167],"respectively.":[168],"Our":[169],"can":[171],"be":[172],"seamlessly":[173],"integrated":[174],"various":[176],"CNN-based":[177],"DETR-based":[179],"models,":[180],"where":[181],"take":[183],"three":[184],"recent":[185,191],"models":[186,210],"KITTI":[188],"model":[192],"NuScenes":[194],"validation.":[196],"Extensive":[197],"experiments":[198],"show":[199],"that":[200],"our":[201],"considerably":[203],"improves":[204],"accuracy":[206,216],"base":[209],"thereby":[212],"achieves":[213],"best":[215],"compared":[217],"with":[218],"all":[219],"recently":[220],"released":[221],"SOTA":[222],"models.":[223]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-11T00:00:00"}