{"id":"https://openalex.org/W4415428428","doi":"https://doi.org/10.3233/faia251111","title":"Efficient Semi-DETR: Real Time End-to-End Semi-Supervised Object Detection","display_name":"Efficient Semi-DETR: Real Time End-to-End Semi-Supervised Object Detection","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428428","doi":"https://doi.org/10.3233/faia251111"},"language":null,"primary_location":{"id":"doi:10.3233/faia251111","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251111","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251111","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057474044","display_name":"Zihao Xin","orcid":"https://orcid.org/0000-0003-4955-885X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zihao Xin","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103132665","display_name":"Wentong Li","orcid":"https://orcid.org/0000-0002-2715-0995"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentong Li","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061215231","display_name":"Jie Qin","orcid":"https://orcid.org/0000-0002-0306-534X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Qin","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103204774","display_name":"Sheng-Jun Huang","orcid":"https://orcid.org/0000-0002-7673-5367"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengjun Huang","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057474044"],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68128823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.933899998664856,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.933899998664856,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9132000207901001,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9099000096321106,"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":0.6948000192642212},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6927000284194946},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6592000126838684},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4244999885559082},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.38089999556541443},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.36000001430511475},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.34790000319480896},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.3294000029563904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767999768257141},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6948000192642212},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6927000284194946},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6592000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45899999141693115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44209998846054077},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4194999933242798},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.3294000029563904},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.32420000433921814},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251111","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251111","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251111","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251111","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"DETR-based":[1],"methods":[2,62],"have":[3],"achieved":[4],"considerable":[5],"success":[6],"in":[7],"semi-supervised":[8,92],"object":[9,93],"detection":[10,94,144],"(SSOD),":[11],"several":[12],"challenges":[13],"remain":[14],"unresolved:":[15],"(1)":[16],"To":[17,83,125],"obtain":[18],"higher-quality":[19],"pseudo-labels":[20,69],"for":[21],"training,":[22],"teacher":[23],"models":[24],"often":[25,75],"adopt":[26],"larger-scale":[27],"architectures,":[28],"which":[29,113],"severely":[30],"impacts":[31],"inference":[32,105,167],"speed.":[33],"In":[34],"contrast,":[35],"lightweight":[36,90],"detectors":[37],"may":[38],"compromise":[39],"the":[40,50,64,127,143,158],"effectiveness":[41],"of":[42,67,129,145,157,173],"existing":[43,174],"SSOD":[44],"methods.":[45,175],"(2)":[46],"Bipartite":[47],"matching":[48],"utilizing":[49],"Hungarian":[51],"algorithm":[52],"does":[53],"not":[54],"fully":[55],"leverage":[56],"potentially":[57,122],"valuable":[58,123],"pseudo-labels.":[59,124],"(3)":[60],"Current":[61],"alleviate":[63],"negative":[65],"impact":[66],"low-quality":[68],"through":[70],"one-to-many":[71],"assignment,":[72],"yet":[73],"this":[74],"leads":[76],"to":[77,100,119,137],"issues":[78],"such":[79],"as":[80],"duplicate":[81,130],"detections.":[82],"tackle":[84,126],"these":[85],"challenges,":[86],"we":[87,107,132],"propose":[88,133],"a":[89,109,115,171],"end-to-end":[91],"framework":[95],"called":[96],"Efficient":[97,134,149],"Semi-DETR.":[98],"Specifically,":[99],"improve":[101,138],"accuracy":[102],"while":[103,165],"reducing":[104],"latency,":[106],"introduce":[108],"heterogeneous":[110],"teacher-student":[111],"framework,":[112],"leverages":[114],"Collaborative":[116],"Auxiliary":[117],"Head":[118],"better":[120],"mine":[121],"issue":[128],"detections,":[131],"Query":[135],"Matching":[136],"training":[139],"efficiency":[140],"and":[141],"enhance":[142],"small":[146],"objects.":[147],"Notably,":[148],"Semi-DETR":[150],"achieves":[151],"44.92":[152],"mAP":[153],"with":[154],"only":[155,170],"10%":[156],"annotated":[159],"MS-COCO":[160],"data,":[161],"surpassing":[162],"state-of-the-art":[163],"methods,":[164],"its":[166],"latency":[168],"is":[169],"quarter":[172]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}