{"id":"https://openalex.org/W4416750062","doi":"https://doi.org/10.1109/iros60139.2025.11247216","title":"Consistent Feature Alignment for Cross-Modal Knowledge Distillation in Monocular 3D Object Detection","display_name":"Consistent Feature Alignment for Cross-Modal Knowledge Distillation in Monocular 3D Object Detection","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750062","doi":"https://doi.org/10.1109/iros60139.2025.11247216"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100373567","display_name":"Fan Li","orcid":"https://orcid.org/0000-0002-3929-6625"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Li","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007211058","display_name":"Rui Ding","orcid":"https://orcid.org/0000-0002-8174-1438"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Ding","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037055449","display_name":"Meng Yang","orcid":"https://orcid.org/0000-0002-0525-5059"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yang","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006277484","display_name":"Xuguang Lan","orcid":"https://orcid.org/0000-0002-3422-944X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuguang Lan","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"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":"2539","last_page":"2546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9437999725341797,"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":0.9437999725341797,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.005100000184029341,"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":0.004999999888241291,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lidar","display_name":"Lidar","score":0.7081000208854675},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6570000052452087},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5898000001907349},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5831999778747559},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.5544999837875366},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5494999885559082},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4555000066757202},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4113999903202057}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7742999792098999},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.7081000208854675},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7044000029563904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6937000155448914},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6570000052452087},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5898000001907349},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5831999778747559},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4081999957561493},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.32019999623298645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C193581530","wikidata":"https://www.wikidata.org/wiki/Q683778","display_name":"Structured light","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.26109999418258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2150066425","https://openalex.org/W2949708697","https://openalex.org/W2954174912","https://openalex.org/W2961317571","https://openalex.org/W2963809933","https://openalex.org/W2968296999","https://openalex.org/W3035461736","https://openalex.org/W3096609285","https://openalex.org/W3106834807","https://openalex.org/W3169690993","https://openalex.org/W3173668541","https://openalex.org/W3176319743","https://openalex.org/W3193939309","https://openalex.org/W3204439495","https://openalex.org/W3215100485","https://openalex.org/W4312461898","https://openalex.org/W4312713480","https://openalex.org/W4382240277","https://openalex.org/W4383066393","https://openalex.org/W4387185258","https://openalex.org/W4387968184","https://openalex.org/W4390871891","https://openalex.org/W4390873008","https://openalex.org/W4399039298","https://openalex.org/W4402704555","https://openalex.org/W4402727763","https://openalex.org/W4402754236","https://openalex.org/W4402952510","https://openalex.org/W4403183568"],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0],"knowledge":[1],"distillation":[2],"(CMKD)":[3],"in":[4,36,109,130,150,197],"monocular":[5,177,220],"3D":[6,178,221],"object":[7,179,222],"detection":[8,223],"transfers":[9],"LiDAR\u2019s":[10],"accurate":[11],"depth":[12],"information":[13],"to":[14,66,128,146,154,175,199,218,264],"compensate":[15],"for":[16,138,173],"the":[17,27,31,38,68,95,139,143,161,184,192,201,229,240,249],"limitations":[18],"of":[19,30,71,78,142,191,204],"camera":[20,44,81,207],"model.":[21],"However,":[22],"current":[23],"methods":[24],"directly":[25],"align":[26,156,200],"intermediate":[28,76,140,158,202],"features":[29,77,85,100,121,141,159,203],"teacher":[32,127,162,193],"and":[33,43,61,80,104,117,194,206,210,233,256,259],"student":[34,129,144,195],"networks,":[35,196],"which":[37],"modality":[39,69,112],"gap":[40,70,113],"between":[41,115],"LiDAR":[42,79,116,205],"hinders":[45],"their":[46],"effectiveness.":[47],"To":[48],"mitigate":[49],"this":[50],"issue,":[51],"we":[52,227],"design":[53],"two":[54,185],"modules,":[55],"namely,":[56],"Consistent":[57,168],"Alignment":[58,170],"Module":[59,64],"(CAM)":[60],"Deformable":[62],"Adapter":[63],"(DAM)":[65],"reduce":[67,147],"CMKD.":[72,131,151],"The":[73,132],"CAM":[74],"transforms":[75],"into":[82],"some":[83,98],"consistent":[84],"through":[86],"a":[87,135,167],"lightweight":[88],"Target":[89],"Head.":[90],"It":[91],"is":[92],"based":[93],"on":[94,239],"observation":[96],"that":[97,244],"high-level":[99],"such":[101],"as":[102,235],"heatmaps":[103],"depths":[105],"are":[106],"highly":[107],"correlated":[108],"CMKD,":[110],"though":[111],"appears":[114],"camera.":[118],"Therefore,":[119],"these":[120],"can":[122,214],"be":[123,215],"effectively":[124],"transferred":[125],"from":[126],"DAM":[133],"introduces":[134],"deformable":[136],"adapter":[137],"network":[145,171,182],"background":[148],"noise":[149],"This":[152],"helps":[153],"dynamically":[155],"its":[157],"with":[160],"network.":[163],"We":[164],"then":[165],"propose":[166],"Feature":[169],"(MonoCFA)":[172],"CMKD":[174,266],"boost":[176],"detection.":[180],"Our":[181,212],"integrates":[183],"designed":[186],"modules":[187],"at":[188],"different":[189],"levels":[190],"order":[198],"more":[208],"accurately":[209],"reliably.":[211],"model":[213],"widely":[216],"applied":[217],"existing":[219],"models.":[224,237,267],"For":[225],"validation,":[226],"choose":[228],"representative":[230],"MonoDLE,":[231],"GUPNet,":[232],"DID-M3D":[234],"base":[236,251],"Experiments":[238],"KITTI":[241],"benchmark":[242],"show":[243],"our":[245],"method":[246],"significantly":[247],"outperforms":[248],"three":[250],"models":[252],"by":[253],"39%,":[254],"15.5%,":[255],"15%,":[257],"respectively,":[258],"achieves":[260],"state-of-the-art":[261],"when":[262],"compared":[263],"other":[265]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}