{"id":"https://openalex.org/W4413359861","doi":"https://doi.org/10.1109/access.2025.3600840","title":"ISDC-YOLO: A Lightweight Small Object Detection Algorithm Based on Inverted Bottleneck and Semantic Detail Fusion Network for UAV Aerial Image","display_name":"ISDC-YOLO: A Lightweight Small Object Detection Algorithm Based on Inverted Bottleneck and Semantic Detail Fusion Network for UAV Aerial Image","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413359861","doi":"https://doi.org/10.1109/access.2025.3600840"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3600840","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3600840","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":null,"license_id":null,"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.2025.3600840","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chen Wang","orcid":"https://orcid.org/0009-0000-1092-6147"},"institutions":[{"id":"https://openalex.org/I133270356","display_name":"Tianjin University of Technology and Education","ror":"https://ror.org/035gwtk09","country_code":"CN","type":"education","lineage":["https://openalex.org/I133270356"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["Electronic Engineering Department, Tianjin University of Technology and Education, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0000-1092-6147","affiliations":[{"raw_affiliation_string":"Electronic Engineering Department, Tianjin University of Technology and Education, Tianjin, China","institution_ids":["https://openalex.org/I133270356"]}]},{"author_position":"last","author":{"id":null,"display_name":"Fen Liu","orcid":"https://orcid.org/0009-0009-5658-1637"},"institutions":[{"id":"https://openalex.org/I133270356","display_name":"Tianjin University of Technology and Education","ror":"https://ror.org/035gwtk09","country_code":"CN","type":"education","lineage":["https://openalex.org/I133270356"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fen Liu","raw_affiliation_strings":["Electronic Engineering Department, Tianjin University of Technology and Education, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0009-5658-1637","affiliations":[{"raw_affiliation_string":"Electronic Engineering Department, Tianjin University of Technology and Education, Tianjin, China","institution_ids":["https://openalex.org/I133270356"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133270356"],"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":0.26346062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"147874","last_page":"147891"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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":0.9952999949455261,"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":0.9936000108718872,"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/bottleneck","display_name":"Bottleneck","score":0.8047451972961426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767286479473114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5876156687736511},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5629934072494507},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5563682913780212},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.5366985201835632},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.5019772052764893},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47942060232162476},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4741484522819519},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4560007154941559},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42047318816185},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3360239863395691}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8047451972961426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767286479473114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5876156687736511},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5629934072494507},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5563682913780212},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.5366985201835632},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.5019772052764893},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47942060232162476},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4741484522819519},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4560007154941559},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42047318816185},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3360239863395691},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3600840","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3600840","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c59603f9c6a04965a415ad0a2798901c","is_oa":true,"landing_page_url":"https://doaj.org/article/c59603f9c6a04965a415ad0a2798901c","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 147874-147891 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3600840","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3600840","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":null,"license_id":null,"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":41,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1503655232","https://openalex.org/W1536680647","https://openalex.org/W1972619302","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2808360995","https://openalex.org/W2922509574","https://openalex.org/W2963037989","https://openalex.org/W2963163009","https://openalex.org/W2963857746","https://openalex.org/W2967487473","https://openalex.org/W3012503967","https://openalex.org/W3018757597","https://openalex.org/W3036708415","https://openalex.org/W3111870206","https://openalex.org/W3157042932","https://openalex.org/W3160733999","https://openalex.org/W3164012963","https://openalex.org/W3171660447","https://openalex.org/W3193812270","https://openalex.org/W3206823361","https://openalex.org/W3208645658","https://openalex.org/W3210586215","https://openalex.org/W3210997334","https://openalex.org/W3213063024","https://openalex.org/W4280526090","https://openalex.org/W4283323781","https://openalex.org/W4285792526","https://openalex.org/W4312823573","https://openalex.org/W4313591552","https://openalex.org/W4324061701","https://openalex.org/W4364323060","https://openalex.org/W4381850779","https://openalex.org/W4382795691","https://openalex.org/W4382998706","https://openalex.org/W4385839827","https://openalex.org/W4387350651","https://openalex.org/W4387934891","https://openalex.org/W4400809902","https://openalex.org/W4404199198"],"related_works":["https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969","https://openalex.org/W2284201331","https://openalex.org/W2095903272","https://openalex.org/W1989561795"],"abstract_inverted_index":{"Unmanned":[0],"aerial":[1,7],"vehicle":[2],"(UAV)":[3],"object":[4],"detection":[5,109,169,248],"in":[6,95,206,210],"images":[8,17],"presents":[9],"substantial":[10],"value":[11],"but":[12],"also":[13],"considerable":[14,37],"challenges.":[15],"UAV":[16],"often":[18],"exhibit":[19],"characteristics":[20],"such":[21],"as":[22,108],"a":[23,120,139,143,174,187,252],"high":[24],"proportion":[25],"of":[26,180,204,258],"small":[27,99,117],"objects,":[28,80,100],"dense":[29],"distributions,":[30],"and":[31,58,73,90,98,105,145,183,208,223,228,235,263],"significant":[32],"scale":[33],"variations,":[34],"which":[35,51,67,93],"present":[36],"challenges":[38],"for":[39,77],"accurate":[40],"detection.":[41],"To":[42],"address":[43],"these":[44],"issues,":[45],"we":[46],"propose":[47],"the":[48,64,69,84,87,113,126,168,178,193,219,256,259],"ISDC-YOLO":[49],"algorithm,":[50],"is":[52,74,81,130,150,171],"based":[53,124],"on":[54,116,125,192,237],"inverted":[55],"bottleneck":[56],"structures":[57],"Semantic":[59,144],"Detail":[60,146],"Fusion":[61,147],"techniques.":[62],"First,":[63],"P5":[65],"layer,":[66],"has":[68],"highest":[70],"parameter":[71,214],"count":[72,215],"primarily":[75],"designed":[76,131,151],"detecting":[78,96],"large":[79],"removed":[82],"from":[83,156,163],"backbone.":[85],"Meanwhile,":[86],"P2,":[88],"P3,":[89],"P4":[91],"layers,":[92],"specialize":[94],"medium":[97],"are":[101],"merged,":[102],"with":[103,160,173,199],"P2":[104],"P3":[106],"serving":[107],"heads":[110],"to":[111,132,152],"enhance":[112],"model\u2019s":[114],"focus":[115],"objects.":[118],"Subsequently,":[119],"lightweight":[121,140,253],"C2F-DOB":[122],"module,":[123],"Inverted":[127],"Bottleneck":[128],"architecture,":[129,254],"capture":[133],"richer":[134],"contextual":[135],"information":[136,155,162],"while":[137,212,250],"maintaining":[138,251],"design.":[141],"Next,":[142],"(SDFM)":[148],"module":[149],"fuse":[153],"fine-grained":[154],"shallow":[157],"feature":[158,165],"maps":[159],"semantic":[161],"deep":[164],"maps.":[166],"Finally,":[167],"head":[170],"replaced":[172],"Dynamic":[175],"Head,":[176],"allowing":[177],"integration":[179],"scale,":[181],"spatial,":[182],"task":[184],"awareness":[185],"within":[186],"single":[188],"module.":[189],"Extensive":[190],"experiments":[191],"VisDrone":[194],"dataset":[195],"demonstrate":[196],"that":[197],"compared":[198],"YOLOv8s,":[200],"ISDC-YOLOv8(128)":[201],"achieves":[202,246],"improvements":[203],"9.8%":[205],"Recall":[207,222],"9.2%":[209],"mAP@0.5,":[211],"reducing":[213],"by":[216,226],"47.8%.":[217],"On":[218],"AI-TOD":[220],"dataset,":[221],"mAP@0.5":[224],"increase":[225],"11.7%":[227],"9.3%,":[229],"respectively,":[230],"further":[231],"validating":[232,255],"its":[233],"effectiveness":[234,257],"generalization":[236],"Solar":[238],"Panel":[239],"Defect":[240],"datasets":[241],"(SPDs).":[242],"The":[243],"improved":[244],"model":[245],"enhanced":[247],"accuracy":[249],"proposed":[260],"optimization":[261],"strategies":[262],"outperforming":[264],"other":[265],"classical":[266],"models.":[267]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}