{"id":"https://openalex.org/W7160243569","doi":"https://doi.org/10.1109/wacv61042.2026.00026","title":"IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection","display_name":"IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160243569","doi":"https://doi.org/10.1109/wacv61042.2026.00026"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046390826","display_name":"J. Meier","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087778","display_name":"Dascena (United States)","ror":"https://ror.org/002g7k102","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087778"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Johannes Meier","raw_affiliation_strings":["DeepScenario"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepScenario","institution_ids":["https://openalex.org/I4210087778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135349091","display_name":"Florian G\u00fcnther","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian G\u00fcnther","raw_affiliation_strings":["TU Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Munich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024120642","display_name":"Riccardo Marin","orcid":"https://orcid.org/0000-0003-3270-892X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Riccardo Marin","raw_affiliation_strings":["TU Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Munich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054428785","display_name":"Oussema Dhaouadi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087778","display_name":"Dascena (United States)","ror":"https://ror.org/002g7k102","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oussema Dhaouadi","raw_affiliation_strings":["DeepScenario"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepScenario","institution_ids":["https://openalex.org/I4210087778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028490309","display_name":"Jacques Kaiser","orcid":"https://orcid.org/0000-0001-7487-6185"},"institutions":[{"id":"https://openalex.org/I4210087778","display_name":"Dascena (United States)","ror":"https://ror.org/002g7k102","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacques Kaiser","raw_affiliation_strings":["DeepScenario"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepScenario","institution_ids":["https://openalex.org/I4210087778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135398595","display_name":"Daniel Cremers","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Cremers","raw_affiliation_strings":["TU Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Munich","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046390826"],"corresponding_institution_ids":["https://openalex.org/I4210087778"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92623364,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"191"},"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":0.2770000100135803,"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":0.2770000100135803,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.2353000044822693,"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":0.07800000160932541,"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/active-learning","display_name":"Active learning (machine learning)","score":0.3984000086784363},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35920000076293945},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3456000089645386},{"id":"https://openalex.org/keywords/active-vision","display_name":"Active vision","score":0.30799999833106995},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2808000147342682}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6930999755859375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.585099995136261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5845999717712402},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2150066425","https://openalex.org/W2560544142","https://openalex.org/W2963323244","https://openalex.org/W2978725006","https://openalex.org/W2981857055","https://openalex.org/W3035166710","https://openalex.org/W3035172746","https://openalex.org/W3095809828","https://openalex.org/W3169690993","https://openalex.org/W3173668541","https://openalex.org/W3176319743","https://openalex.org/W3184557372","https://openalex.org/W3188648403","https://openalex.org/W3203485385","https://openalex.org/W3204439495","https://openalex.org/W4200629618","https://openalex.org/W4285813066","https://openalex.org/W4293363567","https://openalex.org/W4312309370","https://openalex.org/W4312443924","https://openalex.org/W4312842574","https://openalex.org/W4312865155","https://openalex.org/W4312933868","https://openalex.org/W4312939270","https://openalex.org/W4313059105","https://openalex.org/W4367146742","https://openalex.org/W4386076514","https://openalex.org/W4386076547","https://openalex.org/W4386918877","https://openalex.org/W4390872581","https://openalex.org/W4390873008","https://openalex.org/W4390873782","https://openalex.org/W4394625674","https://openalex.org/W4399563629","https://openalex.org/W4401109681","https://openalex.org/W4402703046","https://openalex.org/W4402704555","https://openalex.org/W4402753992","https://openalex.org/W4402754144","https://openalex.org/W4402754236","https://openalex.org/W4402770729","https://openalex.org/W4404199198","https://openalex.org/W4404439867","https://openalex.org/W4409704238","https://openalex.org/W4413010312","https://openalex.org/W4413147166","https://openalex.org/W4413156733","https://openalex.org/W4415798895"],"related_works":[],"abstract_inverted_index":{"Monocular":[0],"3D":[1,18,27,72,108,139],"detection":[2,110],"relies":[3],"on":[4,102,197,210],"just":[5,184],"a":[6,112],"single":[7],"camera":[8],"and":[9,26,166,172,179,200],"is":[10,40,55,83],"therefore":[11],"easy":[12],"to":[13,42,47,95,205],"deploy.":[14],"Yet,":[15],"achieving":[16],"reliable":[17],"understanding":[19],"from":[20],"monocular":[21,73,107,138,158],"images":[22],"requires":[23],"substantial":[24],"annotation,":[25],"labels":[28],"are":[29,120,125],"especially":[30],"costly.":[31],"To":[32],"maximize":[33],"performance":[34,51,178],"under":[35],"constrained":[36],"labeling":[37],"budgets,":[38],"it":[39],"essential":[41],"prioritize":[43],"annotating":[44],"samples":[45],"expected":[46],"deliver":[48],"the":[49,56,90,133,142,187,207,211],"largest":[50],"gains.":[52],"This":[53],"prioritization":[54],"focus":[57],"of":[58,186],"active":[59,68,155],"learning.":[60],"Curiously,":[61],"we":[62,130,145,189],"observed":[63],"two":[64],"significant":[65,180],"limitations":[66],"in":[67,89,106],"learning":[69,156],"algorithms":[70],"for":[71,137,157],"object":[74,109],"detection.":[75,140],"First,":[76],"previous":[77],"approaches":[78],"select":[79],"entire":[80],"images,":[81],"which":[82,105],"inefficient,":[84],"as":[85],"non-informative":[86],"instances":[87],"contained":[88],"same":[91,208],"image":[92],"also":[93],"need":[94],"be":[96],"labeled.":[97],"Secondly,":[98],"existing":[99],"methods":[100],"rely":[101],"uncertainty-based":[103],"selection,":[104],"creates":[111],"bias":[113],"toward":[114],"depth":[115],"ambiguity.":[116],"Consequently,":[117],"distant":[118],"objects":[119,124],"selected,":[121],"while":[122],"nearby":[123],"overlooked.To":[126],"address":[127],"these":[128],"limitations,":[129],"propose":[131],"IDEAL-M3D,":[132],"first":[134,143],"instance-level":[135],"pipeline":[136],"For":[141],"time,":[144],"demonstrate":[146],"that":[147],"an":[148],"explicitly":[149],"diverse,":[150],"fast-to-train":[151],"ensemble":[152],"improves":[153],"diversity-driven":[154],"3D.":[159],"We":[160],"induce":[161],"diversity":[162],"with":[163,183],"heterogeneous":[164],"backbones":[165],"task-agnostic":[167],"features,":[168],"loss":[169],"weight":[170],"perturbation,":[171],"time-dependent":[173],"bagging.":[174],"IDEAL-M3D":[175],"shows":[176],"superior":[177],"resource":[181],"savings:":[182],"60%":[185],"annotations,":[188],"achieve":[190],"similar":[191],"or":[192],"better":[193],"AP<inf":[194],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[195],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3D</inf>":[196],"KITTI":[198],"validation":[199],"test":[201],"set":[202],"results":[203],"compared":[204],"training":[206],"detector":[209],"whole":[212],"dataset.":[213]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-05-06T00:00:00"}