{"id":"https://openalex.org/W4409561304","doi":"https://doi.org/10.1109/icvisp64524.2024.10959391","title":"AGSAFormer: An Adaptive Ghost-MLP Gate and Single-Head Self-Attention Transformer for Image Classification","display_name":"AGSAFormer: An Adaptive Ghost-MLP Gate and Single-Head Self-Attention Transformer for Image Classification","publication_year":2024,"publication_date":"2024-12-27","ids":{"openalex":"https://openalex.org/W4409561304","doi":"https://doi.org/10.1109/icvisp64524.2024.10959391"},"language":"en","primary_location":{"id":"doi:10.1109/icvisp64524.2024.10959391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icvisp64524.2024.10959391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 8th International Conference on Vision, Image and Signal Processing (ICVISP)","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":"https://openalex.org/A5100991103","display_name":"Yuan Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144662","display_name":"Xi'an Institute of Optics and Precision Mechanics","ror":"https://ror.org/0444j5556","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210144662"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan Ma","raw_affiliation_strings":["Xi&#x0027;an Institute of Optics and Precision Mechanics of CAS,Xi&#x0027;an,China"],"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an Institute of Optics and Precision Mechanics of CAS,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I4210144662"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010846765","display_name":"Wei Gao","orcid":"https://orcid.org/0000-0003-2257-5684"},"institutions":[{"id":"https://openalex.org/I4210144662","display_name":"Xi'an Institute of Optics and Precision Mechanics","ror":"https://ror.org/0444j5556","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210144662"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Gao","raw_affiliation_strings":["Space Optics Technology Research Laboratory Xi &#x0027;an Institute of Optics and Precision Mechanics of CAS,Xi&#x0027;an,China"],"affiliations":[{"raw_affiliation_string":"Space Optics Technology Research Laboratory Xi &#x0027;an Institute of Optics and Precision Mechanics of CAS,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I4210144662"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101692352","display_name":"Ximing Zhang","orcid":"https://orcid.org/0009-0004-0522-7199"},"institutions":[{"id":"https://openalex.org/I4210144662","display_name":"Xi'an Institute of Optics and Precision Mechanics","ror":"https://ror.org/0444j5556","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210144662"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ximing Zhang","raw_affiliation_strings":["Space Optics Technology Research Laboratory Xi &#x0027;an Institute of Optics and Precision Mechanics of CAS,Xi&#x0027;an,China"],"affiliations":[{"raw_affiliation_string":"Space Optics Technology Research Laboratory Xi &#x0027;an Institute of Optics and Precision Mechanics of CAS,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I4210144662"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100991103"],"corresponding_institution_ids":["https://openalex.org/I4210144662"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27111868,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10320","display_name":"Neural Networks and Applications","score":0.9341999888420105,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9341999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.691591739654541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5646262764930725},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5370810031890869},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4921850264072418},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4779927134513855},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39989975094795227},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1553954780101776},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15121853351593018},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10208269953727722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.691591739654541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5646262764930725},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5370810031890869},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4921850264072418},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4779927134513855},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39989975094795227},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1553954780101776},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15121853351593018},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10208269953727722},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icvisp64524.2024.10959391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icvisp64524.2024.10959391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 8th International Conference on Vision, Image and Signal Processing (ICVISP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2752782242","https://openalex.org/W2883780447","https://openalex.org/W3035414587","https://openalex.org/W3096609285","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3175515048","https://openalex.org/W3190492058","https://openalex.org/W4214588794","https://openalex.org/W4214614183","https://openalex.org/W4226028923","https://openalex.org/W4313170858","https://openalex.org/W4318541578","https://openalex.org/W4385245566","https://openalex.org/W4386076083","https://openalex.org/W4386076539","https://openalex.org/W4390872550","https://openalex.org/W4390872670","https://openalex.org/W4402715877","https://openalex.org/W4402727538","https://openalex.org/W4403944333"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"With":[0],"the":[1,60,84,87,142,154,160,212],"advent":[2],"of":[3,83,175,188],"deep":[4],"learning,":[5],"Transformers":[6,20],"have":[7],"been":[8],"successfully":[9],"adapted":[10],"to":[11,26,131,217],"computer":[12],"vision":[13,150],"tasks,":[14],"garnering":[15],"significant":[16],"attention.":[17],"While":[18],"Vision":[19,229],"(ViTs)":[21],"demonstrate":[22],"superior":[23],"performance":[24,238],"compared":[25],"traditional":[27],"models,":[28,226],"their":[29],"high":[30],"computational":[31,75,100],"requirements":[32],"impede":[33],"widespread":[34],"adoption.":[35],"In":[36,55,215],"this":[37],"paper,":[38],"we":[39,171],"propose":[40],"an":[41],"efficient":[42,52,149,228],"backbone":[43,155],"AGSAFormer,":[44],"a":[45,56,68,107,116,168,185,235],"hybrid":[46],"convolutional":[47],"neural":[48],"network":[49],"(CNN)":[50],"and":[51,63,77,89,115,134,145,222,239],"ViT":[53],"architectures.":[54],"multi-stage":[57],"stacked":[58],"structure,":[59],"AGSAFormer":[61,85],"reconstructs":[62],"optimizes":[64],"basic":[65,103],"modules,":[66],"striking":[67,234],"balance":[69,236],"between":[70,237],"training":[71,176],"efficiency,":[72],"inference":[73,197],"speed,":[74],"cost,":[76],"model":[78,144,183,204],"accuracy.":[79,139],"The":[80,102,182],"overall":[81,138],"structure":[82],"follows":[86],"multistage":[88],"hierarchical":[90],"representations.":[91],"This":[92],"approach":[93],"facilitates":[94],"multi-scale":[95],"feature":[96,113,122,126],"extraction":[97],"while":[98],"mitigating":[99],"overhead.":[101],"AGSA":[104],"block":[105,128],"incorporates":[106],"window":[108],"attention":[109],"mechanism":[110],"for":[111,120,196],"local":[112,135],"processing":[114,127],"Gated":[117],"Linear":[118],"Unit":[119],"global":[121,133],"processing.":[123],"An":[124],"adaptive":[125],"is":[129,205],"employed":[130],"integrate":[132],"information,":[136],"enhancing":[137],"Without":[140],"using":[141],"teacher":[143],"additional":[146],"data,":[147],"our":[148,203,227],"transformer":[151],"serves":[152],"as":[153,209,211],"network,":[156],"was":[157],"trained":[158],"on":[159,201],"widely":[161],"adopted":[162],"ImageNet-lK":[163],"image":[164],"classification":[165],"dataset.":[166],"Utilizing":[167],"single":[169],"GPU,":[170],"completed":[172],"300":[173],"epochs":[174],"in":[177,198],"less":[178],"than":[179],"48":[180],"hours.":[181],"achieved":[184],"Top-l":[186],"accuracy":[187],"74.5%,":[189],"surpassing":[190],"existing":[191],"baseline":[192,213],"(EfficientVit).":[193],"When":[194],"deployed":[195],"ONNX":[199],"format":[200],"CPU,":[202],"<tex":[206],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[207],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2\\times$</tex>":[208],"fast":[210],"algorithm.":[214],"comparison":[216],"current":[218],"larger-scale":[219],"Transformer":[220,230],"architectures":[221],"other":[223],"state-of-theart":[224],"CNN":[225],"exhibits":[231],"competitive":[232],"results,":[233],"efficiency.":[240]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}