{"id":"https://openalex.org/W7105700427","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229240","title":"SO-DETR: Leveraging Dual-Domain Features and Knowledge Distillation for Small Object Detection","display_name":"SO-DETR: Leveraging Dual-Domain Features and Knowledge Distillation for Small Object Detection","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105700427","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229240"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229240","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":null,"display_name":"Huaxiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huaxiang Zhang","raw_affiliation_strings":["Fudan University,Academy for Engineering and Technology,Shanghai,China,200433"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering and Technology,Shanghai,China,200433","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Fudan University,Academy for Engineering and Technology,Shanghai,China,200433"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering and Technology,Shanghai,China,200433","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aoran Mei","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aoran Mei","raw_affiliation_strings":["Fudan University,Academy for Engineering and Technology,Shanghai,China,200433"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering and Technology,Shanghai,China,200433","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhongxue Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongxue Gan","raw_affiliation_strings":["Fudan University,Academy for Engineering and Technology,Shanghai,China,200433"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering and Technology,Shanghai,China,200433","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":null,"display_name":"Guo-Niu Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo-Niu Zhu","raw_affiliation_strings":["Fudan University,Academy for Engineering and Technology,Shanghai,China,200433"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering and Technology,Shanghai,China,200433","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":12.1808,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.98783275,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"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":0.954800009727478,"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":0.954800009727478,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.014000000432133675,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.004999999888241291,"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/initialization","display_name":"Initialization","score":0.6816999912261963},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6251000165939331},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5849000215530396},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5831999778747559},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5325999855995178},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4406000077724457},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4318999946117401},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4077000021934509},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.40450000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824999988079071},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6816999912261963},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6251000165939331},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5849000215530396},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5831999778747559},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5325999855995178},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5120999813079834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47279998660087585},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4406000077724457},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4318999946117401},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41990000009536743},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36559998989105225},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.263700008392334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229240","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321851","display_name":"Fudan University","ror":"https://ror.org/013q1eq08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2989611864","https://openalex.org/W3013211776","https://openalex.org/W3092151103","https://openalex.org/W3096609285","https://openalex.org/W3134040756","https://openalex.org/W3205100603","https://openalex.org/W4214627427","https://openalex.org/W4312312588","https://openalex.org/W4312823573","https://openalex.org/W4313172897","https://openalex.org/W4320002812","https://openalex.org/W4386072246","https://openalex.org/W4390872670","https://openalex.org/W4390873303","https://openalex.org/W4401415788","https://openalex.org/W4402704578","https://openalex.org/W4402754006","https://openalex.org/W4403770406"],"related_works":[],"abstract_inverted_index":{"Detection":[0,56],"Transformer-based":[1],"methods":[2,165],"have":[3],"achieved":[4],"significant":[5],"advancements":[6],"in":[7,14],"general":[8],"object":[9],"detection.":[10],"However,":[11],"challenges":[12],"remain":[13],"effectively":[15,39],"detecting":[16],"small":[17,42,150],"objects.":[18,43,151],"One":[19],"key":[20,63],"difficulty":[21],"is":[22,173],"that":[23,161],"existing":[24,164],"encoders":[25],"struggle":[26],"to":[27,88],"efficiently":[28],"fuse":[29,89],"low-level":[30],"features.":[31],"Additionally,":[32],"the":[33,96,126,155],"query":[34,71,109,113,129],"selection":[35,72,110],"strategies":[36],"are":[37],"not":[38],"tailored":[40],"for":[41,149],"To":[44],"address":[45],"these":[46],"challenges,":[47],"this":[48],"paper":[49],"proposes":[50],"an":[51,69,146],"efficient":[52,147],"model,":[53],"Small":[54],"Object":[55],"Transformer":[57],"(SO-DETR).":[58],"The":[59,79,107,170],"model":[60],"comprises":[61],"three":[62],"components:":[64],"a":[65,75,134,140],"dual-domain":[66,80],"hybrid":[67,81],"encoder,":[68],"enhanced":[70,108],"mechanism,":[73],"and":[74,85,138,157],"knowledge":[76,141],"distillation":[77,142],"strategy.":[78],"encoder":[82],"integrates":[83],"spatial":[84],"frequency":[86],"domains":[87],"multi-scale":[90],"features":[91,100],"effectively.":[92],"This":[93],"approach":[94],"enhances":[95],"representation":[97],"of":[98,128],"high-resolution":[99],"while":[101],"maintaining":[102],"relatively":[103],"low":[104],"computational":[105,168],"overhead.":[106],"mechanism":[111],"optimizes":[112],"initialization":[114],"by":[115,132],"dynamically":[116],"selecting":[117],"high-scoring":[118],"anchor":[119],"boxes":[120],"using":[121],"expanded":[122],"IoU,":[123],"thereby":[124],"improving":[125],"allocation":[127],"resources.":[130],"Furthermore,":[131],"incorporating":[133],"lightweight":[135],"backbone":[136],"network":[137],"implementing":[139],"strategy,":[143],"we":[144],"develop":[145],"detector":[148],"Experimental":[152],"results":[153],"on":[154],"VisDrone-2019-DET":[156],"UAVVaste":[158],"datasets":[159],"demonstrate":[160],"SO-DETR":[162],"outperforms":[163],"with":[166],"similar":[167],"demands.":[169],"project":[171],"page":[172],"available":[174],"at":[175],"https://github.com/ValiantDiligent/SODETR.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}