{"id":"https://openalex.org/W4416250386","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228116","title":"DyFusion-YOLO: An Enhanced Model for Small Object Detection in Aerial Imagery","display_name":"DyFusion-YOLO: An Enhanced Model for Small Object Detection in Aerial Imagery","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250386","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228116"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5100352773","display_name":"Xinyu Wang","orcid":"https://orcid.org/0000-0001-9082-094X"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyu Wang","raw_affiliation_strings":["Qufu Normal University,School of Cyber Science and Engineering,Jining,China"],"affiliations":[{"raw_affiliation_string":"Qufu Normal University,School of Cyber Science and Engineering,Jining,China","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512591","display_name":"Yude Wang","orcid":"https://orcid.org/0000-0001-6580-7081"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yude Wang","raw_affiliation_strings":["Qufu Normal University,School of Cyber Science and Engineering,Jining,China"],"affiliations":[{"raw_affiliation_string":"Qufu Normal University,School of Cyber Science and Engineering,Jining,China","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105533996","display_name":"Teng Liu","orcid":"https://orcid.org/0009-0004-1017-1679"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Liu","raw_affiliation_strings":["Qufu Normal University,School of Cyber Science and Engineering,Jining,China"],"affiliations":[{"raw_affiliation_string":"Qufu Normal University,School of Cyber Science and Engineering,Jining,China","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051614911","display_name":"Haoyu Guo","orcid":"https://orcid.org/0000-0002-5741-9385"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]},{"id":"https://openalex.org/I4210093349","display_name":"Jining Normal University","ror":"https://ror.org/00he9fz79","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210093349"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Guo","raw_affiliation_strings":["Qufu Normal University,School of Physics and Physical Engineering,Jining,China"],"affiliations":[{"raw_affiliation_string":"Qufu Normal University,School of Physics and Physical Engineering,Jining,China","institution_ids":["https://openalex.org/I202126657","https://openalex.org/I4210093349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101634769","display_name":"Yulin Wang","orcid":"https://orcid.org/0009-0002-2940-1150"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanpei Wang","raw_affiliation_strings":["Qufu Normal University,School of Cyber Science and Engineering,Jining,China"],"affiliations":[{"raw_affiliation_string":"Qufu Normal University,School of Cyber Science and Engineering,Jining,China","institution_ids":["https://openalex.org/I202126657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039668206","display_name":"Fei Song","orcid":"https://orcid.org/0000-0003-0636-8343"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Song","raw_affiliation_strings":["Qufu Normal University,School of Cyber Science and Engineering,Jining,China"],"affiliations":[{"raw_affiliation_string":"Qufu Normal University,School of Cyber Science and Engineering,Jining,China","institution_ids":["https://openalex.org/I202126657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100352773"],"corresponding_institution_ids":["https://openalex.org/I202126657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37305801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9229000210762024,"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":0.9229000210762024,"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/T13918","display_name":"Advanced Data and IoT Technologies","score":0.005100000184029341,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.004699999932199717,"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":0.7653999924659729},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.6717000007629395},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.619700014591217},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6014000177383423},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5436000227928162},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4609000086784363},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4530999958515167},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4406999945640564},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43299999833106995},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4205000102519989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670999765396118},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7653999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7455999851226807},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.6717000007629395},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6363999843597412},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.619700014591217},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6014000177383423},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5436000227928162},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.40619999170303345},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C2780156472","wikidata":"https://www.wikidata.org/wiki/Q2355550","display_name":"Pedestrian detection","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.2831000089645386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2630999982357025},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.259799987077713},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":28,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2109255472","https://openalex.org/W2193145675","https://openalex.org/W2504335775","https://openalex.org/W2565639579","https://openalex.org/W2766585573","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963857746","https://openalex.org/W2997747012","https://openalex.org/W3034552520","https://openalex.org/W3122173535","https://openalex.org/W3138516171","https://openalex.org/W3177052299","https://openalex.org/W3208645658","https://openalex.org/W4256080149","https://openalex.org/W4289752563","https://openalex.org/W4319663728","https://openalex.org/W4372347372","https://openalex.org/W4386076325","https://openalex.org/W4390873988","https://openalex.org/W4394823983","https://openalex.org/W4399207891","https://openalex.org/W4400527330","https://openalex.org/W4402353464","https://openalex.org/W4402754006"],"related_works":[],"abstract_inverted_index":{"Aiming":[0],"at":[1,134],"the":[2,35,47,61,85,97,107,119,139,142,146,155,166,175,188,196,210],"problem":[3],"of":[4,87,99,121,141,157,198],"leakage":[5],"and":[6,19,27,51,53,78,91,123,183,186,209],"false":[7],"detection":[8,12,115,189,223],"in":[9,138],"aerial":[10,221],"image":[11],"due":[13,102],"to":[14,83,103,117,144,180],"complex":[15,158],"background,":[16],"variable":[17],"size":[18],"insufficient":[20],"feature":[21,56,89],"extraction,":[22],"this":[23],"paper":[24],"improves":[25,187],"YOLOv8n":[26],"designs":[28],"a":[29,70,111,128,135,169],"model":[30,147,167],"named":[31],"DyFusion-YOLO.":[32],"It":[33],"optimises":[34],"C2f":[36],"module":[37,66,72],"by":[38,204],"introducing":[39],"dynamic":[40],"snake":[41],"convolution,":[42],"which":[43,173,216],"can":[44],"adaptively":[45],"adjust":[46],"convolution":[48],"kernel":[49],"morphology":[50],"size,":[52],"enhance":[54,84,118],"object":[55,114,163,222],"capture":[57],"capability.":[58],"In":[59],"addition,":[60],"original":[62],"spatial":[63,75],"pyramid":[64,76],"pooling":[65,77],"is":[67,132,202,213,217],"replaced":[68],"with":[69,207],"new":[71,112,170],"that":[73,195],"combines":[74],"cross-stage":[79],"partial":[80],"connectivity":[81],"mechanism":[82,131],"ability":[86],"multi-scale":[88],"fusion":[90,120],"contextual":[92],"information":[93,101],"capture.":[94],"To":[95],"address":[96],"loss":[98,171],"semantic":[100,125],"target":[104],"scale":[105],"inconsistency,":[106],"study":[108],"also":[109],"adds":[110],"small":[113,162],"layer":[116],"deep":[122],"shallow":[124],"information.":[126],"Meanwhile,":[127],"global":[129],"attention":[130,179],"introduced":[133],"key":[136,151],"position":[137],"neck":[140],"network":[143],"make":[145],"focus":[148],"more":[149,178,218],"on":[150,161,200],"channels,":[152],"thus":[153],"reducing":[154],"interference":[156],"background":[159],"noise":[160],"detection.":[164],"Finally,":[165],"adopts":[168],"function,":[172],"makes":[174],"training":[176],"pay":[177],"high-quality":[181],"samples":[182],"localization":[184],"accuracy,":[185],"accuracy.":[190],"The":[191],"final":[192],"results":[193],"show":[194],"mAP50":[197],"DyFusion-YOLO":[199],"VisDrone2019":[201],"improved":[203],"7.0%":[205],"compared":[206],"YOLOv8n,":[208],"computation":[211],"speed":[212],"significantly":[214],"faster,":[215],"suitable":[219],"for":[220],"tasks.":[224]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}