{"id":"https://openalex.org/W7171976919","doi":"https://doi.org/10.1145/3774521.3774563","title":"Rethinking Detection Heads: Enhancing YOLO for Drone Image Object Detection","display_name":"Rethinking Detection Heads: Enhancing YOLO for Drone Image Object Detection","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7171976919","doi":"https://doi.org/10.1145/3774521.3774563"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774563","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774563","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774563","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144163226","display_name":"Rutvik Patel","orcid":"https://orcid.org/0009-0005-1909-0629"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rutvik Patel","raw_affiliation_strings":["Indian Institute of Technology Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0009-0005-1909-0629","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020712489","display_name":"Anureet Chhabra","orcid":"https://orcid.org/0000-0001-8123-4359"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anureet Chhabra","raw_affiliation_strings":["Indian Institute of Technology Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0001-8123-4359","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004999331","display_name":"Ankita Raj","orcid":"https://orcid.org/0000-0003-1068-9406"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ankita Raj","raw_affiliation_strings":["Indian Institute of Technology Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0003-1068-9406","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101532736","display_name":"Chetan Arora","orcid":"https://orcid.org/0000-0003-0155-0250"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chetan Arora","raw_affiliation_strings":["Indian Institute of Technology Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0003-0155-0250","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I68891433"],"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.8277000188827515},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.7608000040054321},{"id":"https://openalex.org/keywords/viola\u2013jones-object-detection-framework","display_name":"Viola\u2013Jones object detection framework","score":0.517300009727478},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.5040000081062317},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4717000126838684},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.45730000734329224},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.44670000672340393},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4205000102519989},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3614000082015991}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.8277000188827515},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.7608000040054321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733299970626831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6963000297546387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6754999756813049},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.517300009727478},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.44670000672340393},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.3513999879360199},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.30880001187324524},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.3027999997138977},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774563","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774563","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774563","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774563","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2193145675","https://openalex.org/W2608264083","https://openalex.org/W2772489440","https://openalex.org/W2962749812","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963995737","https://openalex.org/W2964241181","https://openalex.org/W3036271496","https://openalex.org/W3047386722","https://openalex.org/W3096609285","https://openalex.org/W3160733999","https://openalex.org/W3176659256","https://openalex.org/W3205100603","https://openalex.org/W3207919963","https://openalex.org/W3210586215","https://openalex.org/W4214627427","https://openalex.org/W4328125637","https://openalex.org/W4385453234","https://openalex.org/W4385801363","https://openalex.org/W4390873750","https://openalex.org/W4395028341","https://openalex.org/W4396605538","https://openalex.org/W4398756379","https://openalex.org/W4403888306","https://openalex.org/W4409364193","https://openalex.org/W4415795831","https://openalex.org/W6893711219"],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"addresses":[2],"the":[3,52,64,88,96,122,128,134,148,152,155],"problem":[4],"of":[5,56,66,145,151],"object":[6,74],"detection":[7,18,69,85,98,124,165],"in":[8,47,103],"drone":[9],"imagery,":[10],"which":[11,44],"presents":[12],"distinct":[13],"challenges":[14],"compared":[15],"to":[16,20,51,63],"ground-based":[17],"due":[19,50],"factors":[21],"such":[22],"as":[23],"variable":[24],"flight":[25],"altitudes,":[26],"weather":[27],"conditions,":[28],"and":[29,160,172],"lighting":[30],"variations.":[31],"Existing":[32],"state-of-the-art":[33],"detectors,":[34],"including":[35],"YOLO-based":[36,168],"architectures,":[37],"often":[38],"struggle":[39],"with":[40],"detecting":[41],"ultra-small":[42,73],"objects,":[43],"frequently":[45],"appear":[46],"aerial":[48,104],"perspectives":[49],"higher":[53],"vantage":[54],"point":[55],"drones.":[57],"Our":[58],"analysis":[59,93],"attributes":[60],"this":[61],"limitation":[62],"absence":[65],"a":[67,140],"dedicated":[68],"head":[70,86,99],"tailored":[71],"for":[72],"detection.":[75],"As":[76],"our":[77,117,137],"first":[78],"contribution,":[79],"we":[80],"introduce":[81],"an":[82],"additional":[83],"ultra-small-object":[84],"into":[87],"YOLOv11":[89],"architecture.":[90],"Furthermore,":[91],"empirical":[92],"reveals":[94],"that":[95],"large-object":[97,123],"offers":[100],"negligible":[101],"benefit":[102],"scenarios,":[105],"where":[106],"targets":[107],"are":[108,158],"typically":[109],"captured":[110],"from":[111],"altitudes":[112],"exceeding":[113],"10":[114],"meters.":[115],"Consequently,":[116],"second":[118],"contribution":[119],"involves":[120],"removing":[121],"head,":[125],"thereby":[126],"simplifying":[127],"architecture":[129],"without":[130],"sacrificing":[131],"accuracy.":[132],"On":[133],"VisDrone":[135],"benchmark,":[136],"approach":[138],"attains":[139],"mean":[141],"Average":[142],"Precision":[143],"(mAP)":[144],"40.62%,":[146],"surpassing":[147],"current":[149],"state":[150],"art.":[153],"Moreover,":[154],"proposed":[156],"modifications":[157],"modular":[159],"transferable,":[161],"enabling":[162],"improved":[163],"small-object":[164],"across":[166],"other":[167],"detectors.":[169],"Full":[170],"source-code":[171],"pretrained":[173],"models":[174],"will":[175],"be":[176],"made":[177],"publicly":[178],"available":[179],"upon":[180],"acceptance.":[181]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}