{"id":"https://openalex.org/W7167083009","doi":"https://doi.org/10.1109/access.2026.3709299","title":"FFG-YOLO: An Accuracy-Oriented Multi-Dimensional Feature Enhancement Framework for Small Object Detection in UAV Imagery","display_name":"FFG-YOLO: An Accuracy-Oriented Multi-Dimensional Feature Enhancement Framework for Small Object Detection in UAV Imagery","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7167083009","doi":"https://doi.org/10.1109/access.2026.3709299"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3709299","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3709299","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3709299","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102119252","display_name":"Du Chen","orcid":"https://orcid.org/0009-0009-0172-6317"},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Du Chen","raw_affiliation_strings":["School of Information and Communication Engineering, East China Jiaotong University, Nanchang, China"],"raw_orcid":"https://orcid.org/0009-0008-4098-264X","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, East China Jiaotong University, Nanchang, China","institution_ids":["https://openalex.org/I13985625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139943009","display_name":"Yi-Feng Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-Feng Xiao","raw_affiliation_strings":["School of Information and Communication Engineering, East China Jiaotong University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, East China Jiaotong University, Nanchang, China","institution_ids":["https://openalex.org/I13985625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035454138","display_name":"Zhao Wen-jie","orcid":null},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen-Jie Zhao","raw_affiliation_strings":["School of Information and Communication Engineering, East China Jiaotong University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, East China Jiaotong University, Nanchang, China","institution_ids":["https://openalex.org/I13985625"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139855308","display_name":"Jun-Feng Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun-Feng Zou","raw_affiliation_strings":["School of Information and Communication Engineering, East China Jiaotong University, Nanchang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, East China Jiaotong University, Nanchang, China","institution_ids":["https://openalex.org/I13985625"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I13985625"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88414865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"100141","last_page":"100172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7197999954223633,"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":0.7197999954223633,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.03790000081062317,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.020600000396370888,"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/object-detection","display_name":"Object detection","score":0.7053999900817871},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.522599995136261},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43709999322891235},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4196999967098236},{"id":"https://openalex.org/keywords/object-class-detection","display_name":"Object-class detection","score":0.39969998598098755},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3734999895095825},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3450999855995178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777000069618225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7121000289916992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7113000154495239},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7053999900817871},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.39969998598098755},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3450999855995178},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.328000009059906},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.26350000500679016},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3709299","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3709299","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2b81a0b9b5c346c88b376894bd5df276","is_oa":false,"landing_page_url":"https://doaj.org/article/2b81a0b9b5c346c88b376894bd5df276","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 100141-100172 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3709299","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3709299","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Small":[0],"object":[1],"detection":[2],"in":[3],"uncrewed":[4],"aerial":[5],"vehicle":[6],"(UAV)":[7],"imagery":[8],"remains":[9],"challenging":[10],"because":[11],"repeated":[12],"downsampling":[13],"weakens":[14],"tiny-target":[15],"details":[16],"and":[17,55,58,78,93,133,154,166],"conventional":[18],"fusion":[19],"modules":[20],"do":[21],"not":[22],"fully":[23],"recover":[24],"multi-dimensional":[25],"cues.":[26],"We":[27],"propose":[28],"FFG-YOLO,":[29],"an":[30,171,179],"accuracy-oriented":[31],"YOLOv8s":[32,89],"framework":[33],"that":[34],"integrates":[35],"three":[36,65,131,147],"adaptations:":[37],"ConvSPD":[38],"for":[39,48,60,182],"spatial-information-preserving":[40],"downsampling,":[41],"a":[42,103,112,162],"Fine-grained":[43],"Feature":[44],"Generation":[45],"(FFG)":[46],"module":[47],"RepC3-dominated":[49],"contextual":[50],"enhancement":[51],"with":[52],"lightweight":[53],"spatial":[54],"channel":[56],"refinements,":[57],"Focaler-CIoU":[59],"hard-sample-focused":[61],"box":[62],"regression.":[63],"Across":[64],"random":[66],"seeds":[67],"on":[68,123,134,170],"VisDrone2019,":[69],"FFG-YOLO":[70,177],"attains":[71],"<inline-formula>":[72,79],"<tex-math":[73,80],"notation=\"LaTeX\">$49.10~\\pm":[74],"~0.55$":[75],"</tex-math></inline-formula>%":[76,83],"mAP@0.5":[77],"notation=\"LaTeX\">$30.17~\\pm":[81],"~0.39$":[82],"mAP@0.5:0.95,":[84],"improving":[85],"over":[86,130,146],"the":[87,135],"three-seed":[88],"baseline":[90],"by":[91,98],"+10.79":[92],"+6.75":[94],"percentage":[95,128,144],"points,":[96],"supported":[97],"paired":[99],"seed-wise":[100],"consistency":[101],"checks;":[102],"best":[104],"single":[105],"run":[106],"reaches":[107,167],"49.6%":[108],"/":[109,126,142],"30.6%":[110],"under":[111,161],"separate":[113],"batch-32":[114],"single-run":[115],"protocol.":[116],"Matched":[117],"per-dataset":[118],"tests":[119],"show":[120],"retained":[121],"gains":[122],"UAVDT":[124],"(+7.18":[125],"+5.55":[127],"points":[129,145],"seeds)":[132],"more":[136],"general":[137],"DIOR":[138],"remote-sensing":[139],"benchmark":[140],"(+1.46":[141],"+1.14":[143],"seeds).":[148],"The":[149],"model":[150],"has":[151],"63.27M":[152],"parameters":[153],"145.62":[155],"GMACs,":[156],"corresponding":[157],"to":[158],"291.24":[159],"GFLOPs":[160],"two-operation":[163],"MAC":[164],"convention,":[165],"71.23":[168],"FPS":[169],"RTX":[172],"4090.":[173],"These":[174],"results":[175],"position":[176],"as":[178],"accuracy-first":[180],"detector":[181],"ground-station":[183],"or":[184],"offline":[185],"UAV":[186],"image":[187],"analysis":[188],"rather":[189],"than":[190],"resource-constrained":[191],"onboard":[192],"deployment.":[193]},"counts_by_year":[],"updated_date":"2026-07-10T05:49:55.623906","created_date":"2026-07-03T00:00:00"}