{"id":"https://openalex.org/W7160011417","doi":"https://doi.org/10.1109/access.2026.3688760","title":"Dual-Scale Parallel Training: Boosting Scale Generalization for Object Detectors Without Inference Overhead","display_name":"Dual-Scale Parallel Training: Boosting Scale Generalization for Object Detectors Without Inference Overhead","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160011417","doi":"https://doi.org/10.1109/access.2026.3688760"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3688760","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3688760","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2026.3688760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003776747","display_name":"W L Li","orcid":null},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangzhong Li","raw_affiliation_strings":["School of Computer, Electronics and Information, Guangxi University, Nanning, China"],"raw_orcid":"https://orcid.org/0009-0007-7846-1201","affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374441","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-5802-7519"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Li","raw_affiliation_strings":["School of Computer, Electronics and Information, Guangxi University, Nanning, China"],"raw_orcid":"https://orcid.org/0000-0002-3212-0416","affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104227548","display_name":"Xuefeng Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I3129996945","display_name":"Guilin University of Aerospace Technology","ror":"https://ror.org/00h1gc758","country_code":"CN","type":"education","lineage":["https://openalex.org/I3129996945"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Rao","raw_affiliation_strings":["School of Computer Science and Engineering, Guilin University of Aerospace Technology, Guilin, China"],"raw_orcid":"https://orcid.org/0009-0001-9889-3286","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Guilin University of Aerospace Technology, Guilin, China","institution_ids":["https://openalex.org/I3129996945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135216810","display_name":"Xiangmeng Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangmeng Pan","raw_affiliation_strings":["School of Computer, Electronics and Information, Guangxi University, Nanning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135153493","display_name":"Yujie Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujie Zhao","raw_affiliation_strings":["School of Computer, Electronics and Information, Guangxi University, Nanning, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.5148182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"66323","last_page":"66336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7312999963760376,"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":0.7312999963760376,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.03689999878406525,"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/T11448","display_name":"Face recognition and analysis","score":0.026399999856948853,"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/boosting","display_name":"Boosting (machine learning)","score":0.7839000225067139},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6050999760627747},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5774000287055969},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.550599992275238},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.45899999141693115},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4514999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990000247955322},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7839000225067139},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5206000208854675},{"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/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43880000710487366},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.3393000066280365},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26190000772476196}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3688760","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3688760","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bee47f4de3ff4b2bacd671a97aaf6fb9","is_oa":true,"landing_page_url":"https://doaj.org/article/bee47f4de3ff4b2bacd671a97aaf6fb9","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 14, Pp 66323-66336 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3688760","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3688760","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2969484963","display_name":null,"funder_award_id":"2026GXNSFHA00640243","funder_id":"https://openalex.org/F4320329214","funder_display_name":"Guangxi University of Science and Technology"},{"id":"https://openalex.org/G5617228823","display_name":null,"funder_award_id":"20220107-3","funder_id":"https://openalex.org/F4320336618","funder_display_name":"Science and Technology Program of Suzhou"},{"id":"https://openalex.org/G5900592863","display_name":null,"funder_award_id":"2026GXNSFHA00640260","funder_id":"https://openalex.org/F4320329214","funder_display_name":"Guangxi University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320329214","display_name":"Guangxi University of Science and Technology","ror":null},{"id":"https://openalex.org/F4320336618","display_name":"Science and Technology Program of Suzhou","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,149],"object":[1,67,171,191],"detection":[2,13,68,161,192],"tasks,":[3],"scale":[4,20,52],"variation":[5],"is":[6,180],"one":[7],"of":[8,22],"the":[9,19,84,99,108,141,174],"major":[10],"challenges":[11],"affecting":[12],"accuracy.":[14],"Existing":[15],"methods":[16,159],"typically":[17],"enhance":[18],"generalization":[21,104],"models":[23,193],"through":[24,26],"strategies":[25],"image":[27,75],"pyramids,":[28],"feature":[29],"pyramid":[30],"networks,":[31],"or":[32,43,111],"multi-scale":[33,101,157],"training.":[34,55,81],"However,":[35],"these":[36],"approaches":[37],"either":[38],"increase":[39],"inference":[40,112],"computational":[41],"costs":[42],"have":[44],"not":[45],"previously":[46],"established":[47],"explicit":[48],"associations":[49],"between":[50],"different":[51],"inputs":[53],"during":[54,80],"We":[56],"propose":[57],"Dual-Scale":[58],"Parallel":[59],"Training":[60],"(DSPT)":[61],"as":[62],"a":[63,186],"training":[64,158,176,190],"strategy":[65,179],"for":[66,77],"models.":[69],"This":[70],"method":[71],"introduces":[72],"high-and-low-resolution":[73],"homologous":[74],"branches":[76],"associative":[78],"learning":[79],"By":[82],"fusing":[83],"losses":[85],"from":[86],"both":[87],"branches,":[88],"DSPT":[89,118,153],"enables":[90],"shared-parameter,":[91],"same-iteration":[92],"cross-scale":[93],"joint":[94],"optimization":[95],"strategy,":[96],"thereby":[97],"enhancing":[98],"model’s":[100],"perception":[102],"and":[103,133,138,156,163,165,183],"ability":[105],"without":[106],"altering":[107],"network":[109],"structure":[110],"efficiency.":[113],"Experimental":[114],"results":[115],"demonstrate":[116],"that":[117],"achieves":[119],"stable":[120],"performance":[121],"improvements":[122],"across":[123,169],"several":[124],"popular":[125],"datasets":[126],"(MS":[127],"COCO,":[128],"PASCAL":[129],"VOC,":[130],"VisDrone,":[131],"etc.)":[132],"two":[134],"model":[135],"series":[136],"(YOLO":[137],"RT-DETR),":[139],"with":[140,194],"mAP@50":[142],"metric":[143],"improving":[144],"by":[145],"up":[146],"to":[147,189],"4%.":[148],"scale-aware":[150],"evaluation":[151],"experiments,":[152],"outperforms":[154],"conventional":[155],"in":[160],"accuracy":[162],"generalization,":[164],"provides":[166],"positive":[167],"gains":[168],"all":[170],"sizes.":[172],"Despite":[173],"increased":[175],"cost,":[177],"this":[178],"simple,":[181],"general,":[182],"scalable,":[184],"providing":[185],"practical":[187,196],"approach":[188],"promising":[195],"applications.":[197]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-05-05T00:00:00"}