{"id":"https://openalex.org/W7161937905","doi":"https://doi.org/10.48550/arxiv.2605.20669","title":"GSA-YOLO: A High-Efficiency Framework via Structured Sparsity and Adaptive Knowledge Distillation for Real-Time X-ray Security Inspection","display_name":"GSA-YOLO: A High-Efficiency Framework via Structured Sparsity and Adaptive Knowledge Distillation for Real-Time X-ray Security Inspection","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7161937905","doi":"https://doi.org/10.48550/arxiv.2605.20669"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20669","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20669","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.20669","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136691020","display_name":"Jiahao Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kong, Jiahao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5136691020"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6075999736785889,"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":0.6075999736785889,"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/T12386","display_name":"Advanced X-ray and CT Imaging","score":0.06639999896287918,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.05640000104904175,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6680999994277954},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6380000114440918},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4616999924182892},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4458000063896179},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4296000003814697},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.42480000853538513},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3815000057220459},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.3781999945640564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077999711036682},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6680999994277954},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6380000114440918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5498999953269958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5042999982833862},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.461899995803833},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4296000003814697},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C37616216","wikidata":"https://www.wikidata.org/wiki/Q3218363","display_name":"Lasso (programming language)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2780264999","wikidata":"https://www.wikidata.org/wiki/Q7445032","display_name":"Security domain","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20669","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20669","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.20669","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20669","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"X-ray":[0,192],"security":[1,193],"inspection":[2],"requires":[3],"accurate":[4],"real-time":[5],"detection":[6,49,86],"of":[7,19,137,156],"prohibited":[8],"items,":[9],"but":[10],"existing":[11],"models":[12],"often":[13],"struggle":[14],"to":[15,47,71,84,149,174],"balance":[16],"the":[17,42,72,85,123,170],"challenges":[18],"severe":[20],"occlusion,":[21],"complex":[22],"clutter,":[23],"and":[24,51,59,92,125,158,162,166],"strict":[25],"speed":[26,136],"requirements.":[27],"To":[28],"overcome":[29],"these":[30],"challenges,":[31],"this":[32],"paper":[33],"proposes":[34],"GSA-YOLO,":[35],"a":[36,133,142,187],"novel":[37],"lightweight":[38],"framework":[39],"built":[40],"upon":[41],"YOLOv8n":[43],"architecture,":[44],"specifically":[45],"engineered":[46],"enhance":[48],"robustness":[50],"inference":[52,135],"efficiency.":[53],"GSA-YOLO":[54,152,177],"strategically":[55],"integrates":[56],"structured":[57],"sparsity":[58],"adaptive":[60],"knowledge":[61],"transfer":[62],"through":[63],"three":[64],"core":[65],"components:":[66],"Group":[67],"Lasso":[68],"(GL)":[69],"applied":[70,83],"network":[73],"neck":[74],"for":[75,88,99,190],"robust":[76],"feature":[77,108],"extraction;":[78],"Sparse":[79],"Structure":[80],"Selection":[81],"(SSS)":[82],"head":[87],"significant":[89],"model":[90,115],"slimming;":[91],"an":[93],"Adaptive":[94],"Knowledge":[95],"Distillation":[96],"(Ada-KD)":[97],"mechanism":[98],"comprehensive":[100,130],"accuracy":[101,180],"recovery.":[102],"This":[103],"integrated":[104],"approach":[105],"synergistically":[106],"enhances":[107],"representation":[109],"while":[110,181],"pruning":[111],"redundant":[112],"channels,":[113],"maximizing":[114],"efficiency":[116],"without":[117],"sacrificing":[118],"performance.":[119],"Rigorous":[120],"evaluations":[121],"on":[122,160],"HiXray":[124,161],"PIDray":[126],"datasets":[127],"confirm":[128],"GSA-YOLO's":[129],"capability,":[131],"achieving":[132],"leading":[134],"189.62":[138],"FPS,":[139],"accompanied":[140],"by":[141],"reduction":[143],"in":[144],"computational":[145,183],"cost":[146],"from":[147],"8.7G":[148],"8.0G.":[150],"Crucially,":[151],"secures":[153],"mAP50:95":[154],"results":[155],"0.531":[157],"0.679":[159],"PIDray,":[163],"demonstrating":[164],"2.4%":[165],"1.8%":[167],"improvements":[168],"over":[169],"baseline,":[171],"respectively.":[172],"Compared":[173],"other":[175],"models,":[176],"exhibits":[178],"enhanced":[179],"maintaining":[182],"efficiency,":[184],"making":[185],"it":[186],"promising":[188],"solution":[189],"practical":[191],"inspection.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-22T00:00:00"}