{"id":"https://openalex.org/W6891861938","doi":"https://doi.org/10.48550/arxiv.2507.13373","title":"Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection","display_name":"Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection","publication_year":2025,"publication_date":"2025-07-12","ids":{"openalex":"https://openalex.org/W6891861938","doi":"https://doi.org/10.48550/arxiv.2507.13373"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2507.13373","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.13373","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2507.13373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lin, Xiaojian","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lin, Xiaojian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Wenxin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiang, Yuchu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Yuchu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, Wangyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Wangyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Guo, Yiran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yiran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Kangxu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Kangxu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Zongzheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zongzheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Guijin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Guijin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jin, Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Lei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zhao, Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Hao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"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":true,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9610000252723694,"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":0.9610000252723694,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.013799999840557575,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.0038999998942017555,"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/feature","display_name":"Feature (linguistics)","score":0.7440999746322632},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.703499972820282},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6499999761581421},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5512999892234802},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4837999939918518},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.42910000681877136},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42340001463890076},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.41290000081062317},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41029998660087585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583000063896179},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7440999746322632},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.703499972820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6600000262260437},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6499999761581421},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5512999892234802},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4837999939918518},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.37720000743865967},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.362199991941452},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2780217385","wikidata":"https://www.wikidata.org/wiki/Q2389284","display_name":"Hierarchical organization","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2614000141620636},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2507.13373","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.13373","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2507.13373","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.13373","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.603168249130249,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hierarchical":[0,108],"feature":[1,44,72,93,126,139,157],"representations":[2,73],"play":[3],"a":[4,63,171],"pivotal":[5],"role":[6],"in":[7,11,30,146,179],"computer":[8],"vision,":[9],"particularly":[10],"object":[12,65,167],"detection":[13,51,66,76,147,168],"for":[14,22,74],"autonomous":[15,181,200],"driving.":[16],"Multi-level":[17],"semantic":[18,121],"understanding":[19],"is":[20],"crucial":[21],"accurately":[23],"identifying":[24],"pedestrians,":[25],"vehicles,":[26],"and":[27,39,53,103,106,123,134,159,176,186,196],"traffic":[28],"signs":[29],"dynamic":[31],"environments.":[32],"However,":[33],"existing":[34],"architectures,":[35],"such":[36],"as":[37],"YOLO":[38],"DETR,":[40],"struggle":[41],"to":[42,69,100,119,143,166],"maintain":[43],"consistency":[45,94],"across":[46],"different":[47],"scales":[48],"while":[49,149],"balancing":[50],"precision":[52],"computational":[54,177],"efficiency.":[55],"To":[56],"address":[57],"these":[58],"challenges,":[59],"we":[60],"propose":[61],"Butter,":[62],"novel":[64],"framework":[67],"designed":[68],"enhance":[70,101],"hierarchical":[71,125,156],"improving":[75],"robustness.":[77],"Specifically,":[78],"Butter":[79,136,161],"introduces":[80],"two":[81],"key":[82],"innovations:":[83],"Frequency-Adaptive":[84],"Feature":[85,109],"Consistency":[86],"Enhancement":[87],"(FAFCE)":[88],"Component,":[89],"which":[90,114],"refines":[91],"multi-scale":[92],"by":[95],"leveraging":[96],"adaptive":[97],"frequency":[98],"filtering":[99],"structural":[102],"boundary":[104],"precision,":[105],"Progressive":[107],"Fusion":[110],"Network":[111],"(PHFFNet)":[112],"Module,":[113],"progressively":[115],"integrates":[116],"multi-level":[117],"features":[118],"mitigate":[120],"gaps":[122],"strengthen":[124],"learning.":[127],"Through":[128],"extensive":[129],"experiments":[130],"on":[131,155],"BDD100K,":[132],"KITTI,":[133],"Cityscapes,":[135],"demonstrates":[137],"superior":[138],"representation":[140],"capabilities,":[141],"leading":[142],"notable":[144],"improvements":[145],"accuracy":[148],"reducing":[150],"model":[151,185],"complexity.":[152],"By":[153],"focusing":[154],"refinement":[158],"integration,":[160],"provides":[162],"an":[163],"advanced":[164],"approach":[165],"that":[169],"achieves":[170],"balance":[172],"between":[173],"accuracy,":[174],"deployability,":[175],"efficiency":[178],"real-time":[180],"driving":[182,201],"scenarios.":[183],"Our":[184],"implementation":[187],"are":[188],"publicly":[189],"available":[190],"at":[191],"https://github.com/Aveiro-Lin/Butter,":[192],"facilitating":[193],"further":[194],"research":[195],"validation":[197],"within":[198],"the":[199],"community.":[202]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}