{"id":"https://openalex.org/W4416748534","doi":"https://doi.org/10.1109/iros60139.2025.11247171","title":"EDSOD: An Encoder-Decoder, Diffusion-model, and Swin-Transformer-based Small Object Detector","display_name":"EDSOD: An Encoder-Decoder, Diffusion-model, and Swin-Transformer-based Small Object Detector","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748534","doi":"https://doi.org/10.1109/iros60139.2025.11247171"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5006656155","display_name":"Junnian Li","orcid":"https://orcid.org/0000-0003-4257-9594"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junnian Li","raw_affiliation_strings":["Beijing University of Chemical Technology,College of Information Science and Technology,Beijing,China,100029"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Chemical Technology,College of Information Science and Technology,Beijing,China,100029","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081318069","display_name":"MengChu Zhou","orcid":"https://orcid.org/0000-0002-5408-8752"},"institutions":[{"id":"https://openalex.org/I75059550","display_name":"Zhejiang Gongshang University","ror":"https://ror.org/0569mkk41","country_code":"CN","type":"education","lineage":["https://openalex.org/I75059550"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"MengChu Zhou","raw_affiliation_strings":["Zhejiang Gongshang University,School of Information and Electronic Engineering,Hangzhou,China,310018"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Gongshang University,School of Information and Electronic Engineering,Hangzhou,China,310018","institution_ids":["https://openalex.org/I75059550"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079155612","display_name":"Zhengcai Cao","orcid":"https://orcid.org/0000-0003-0344-0207"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4391767639","display_name":"State Key Laboratory of Robotics and Systems","ror":"https://ror.org/015m77g16","country_code":"CN","type":"facility","lineage":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengcai Cao","raw_affiliation_strings":["Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,China,150080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,State Key Laboratory of Robotics and Systems,Harbin,China,150080","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":"1659","last_page":"1665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9491999745368958,"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":0.9491999745368958,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.006399999838322401,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.005400000140070915,"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/minimum-bounding-box","display_name":"Minimum bounding box","score":0.47380000352859497},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46619999408721924},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.45899999141693115},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45350000262260437},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4496000111103058},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4205999970436096},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4154999852180481},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40070000290870667},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.39879998564720154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.590499997138977},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.47380000352859497},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.45899999141693115},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.39879998564720154},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.35190001130104065},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.3292999863624573},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3292999863624573},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.3125},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247171","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322857","display_name":"Aeronautical Science Foundation of China","ror":"https://ror.org/02wq41p38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2952122856","https://openalex.org/W2962777203","https://openalex.org/W2963351448","https://openalex.org/W3026765122","https://openalex.org/W3042916480","https://openalex.org/W3096609285","https://openalex.org/W3116963012","https://openalex.org/W3138516171","https://openalex.org/W3168844623","https://openalex.org/W3172752666","https://openalex.org/W3205100603","https://openalex.org/W3216352822","https://openalex.org/W4312504688","https://openalex.org/W4312609198","https://openalex.org/W4312823573","https://openalex.org/W4382568144","https://openalex.org/W4386071817","https://openalex.org/W4386076053","https://openalex.org/W4390873752","https://openalex.org/W4392450331","https://openalex.org/W4393158955","https://openalex.org/W4394994789","https://openalex.org/W4395028341","https://openalex.org/W4402703028","https://openalex.org/W4402753518","https://openalex.org/W4405787932","https://openalex.org/W4406163715","https://openalex.org/W4406812276"],"related_works":[],"abstract_inverted_index":{"Small":[0],"object":[1],"detection":[2],"(SOD)":[3],"given":[4,80],"aerial":[5,81],"images":[6],"suffers":[7],"from":[8,41],"an":[9,86,96],"information":[10,58],"imbalance":[11],"across":[12],"different":[13,42],"feature":[14,51],"scales.":[15],"This":[16],"makes":[17],"it":[18],"extremely":[19],"challenging":[20],"to":[21,120],"perform":[22],"accurate":[23],"SOD.":[24],"Existing":[25],"methods,":[26],"e.g.,":[27],"Feature":[28],"Pyramid":[29],"Network":[30],"(FPN)-based":[31],"algorithms,":[32],"focus":[33],"on":[34,133],"extracting":[35],"high-resolution":[36],"and":[37,53,77,104,117,122],"low-resolution":[38],"semantic":[39,50],"features":[40],"convolution":[43,48],"layers.":[44],"However,":[45],"in":[46],"deeper":[47],"layers,":[49],"misalignment":[52],"the":[54,130,147,150],"loss":[55],"of":[56,149],"key":[57],"are":[59],"inevitable.":[60],"To":[61],"tackle":[62],"such":[63],"issues,":[64],"this":[65],"work":[66],"proposes":[67],"a":[68,74,90,101,114],"new":[69],"encoder-decoder-based":[70,97],"SOD":[71,87,144],"framework":[72,98,132],"with":[73],"Diffusion":[75],"Model":[76],"Swin":[78,105],"Transformer":[79,106],"images.":[82],"First,":[83],"we":[84],"reformulate":[85],"task":[88],"as":[89],"Noise-to-Box":[91],"process.":[92],"We":[93,112,127],"then":[94],"construct":[95],"by":[99],"using":[100],"diffusion":[102],"model":[103],"for":[107],"dynamic":[108],"bounding":[109],"box":[110],"generation.":[111],"introduce":[113],"decoupling":[115],"training":[116],"inferencing":[118],"strategy":[119],"recognize":[121],"locate":[123],"small":[124],"objects":[125],"accurately.":[126],"finally":[128],"evaluate":[129],"proposed":[131],"several":[134],"public":[135],"benchmarks.":[136],"The":[137],"experimental":[138],"results":[139],"well":[140],"show":[141],"its":[142],"better":[143],"performance":[145],"than":[146],"state":[148],"art.":[151],"Code":[152],"is":[153],"available":[154],"at":[155],"https://github.com/BrainPotter/EDSOD.":[156]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-28T00:00:00"}