{"id":"https://openalex.org/W3162418282","doi":"https://doi.org/10.1109/icassp39728.2021.9414568","title":"SA-Net: Shuffle Attention for Deep Convolutional Neural Networks","display_name":"SA-Net: Shuffle Attention for Deep Convolutional Neural Networks","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162418282","doi":"https://doi.org/10.1109/icassp39728.2021.9414568","mag":"3162418282"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5067844767","display_name":"Qinglong Zhang","orcid":"https://orcid.org/0000-0001-9002-5903"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing-Long Zhang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111673780","display_name":"Yu-Bin Yang","orcid":"https://orcid.org/0000-0002-3764-1114"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Bin Yang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":59.7956,"has_fulltext":false,"cited_by_count":986,"citation_normalized_percentile":{"value":0.99907543,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2235","last_page":"2239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9984999895095825,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"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/flops","display_name":"FLOPS","score":0.826042652130127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8081616163253784},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6273530125617981},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6055480241775513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.579942524433136},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5742014646530151},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5418809652328491},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5308253169059753},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5282745957374573},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5032805800437927},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4368118345737457},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.41996410489082336},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41532444953918457},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4143921732902527},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4120936393737793},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4094393849372864},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.36675894260406494},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.27514970302581787},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0863972008228302}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.826042652130127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081616163253784},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6273530125617981},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6055480241775513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579942524433136},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5742014646530151},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5418809652328491},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5308253169059753},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5282745957374573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5032805800437927},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4368118345737457},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41996410489082336},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41532444953918457},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4143921732902527},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4120936393737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4094393849372864},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36675894260406494},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27514970302581787},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0863972008228302},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":28,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2194775991","https://openalex.org/W2613718673","https://openalex.org/W2622263826","https://openalex.org/W2752782242","https://openalex.org/W2883780447","https://openalex.org/W2884585870","https://openalex.org/W2890782586","https://openalex.org/W2895340641","https://openalex.org/W2922509574","https://openalex.org/W2945164022","https://openalex.org/W2955058313","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963420686","https://openalex.org/W2981408784","https://openalex.org/W2981689412","https://openalex.org/W2981899103","https://openalex.org/W2982220924","https://openalex.org/W2993235622","https://openalex.org/W3034552520","https://openalex.org/W4250482878","https://openalex.org/W6620707391","https://openalex.org/W6739622702","https://openalex.org/W6753412334","https://openalex.org/W6754879843","https://openalex.org/W6756709046","https://openalex.org/W6761855798"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W3102845713","https://openalex.org/W2487162673","https://openalex.org/W2971502891","https://openalex.org/W2793211469","https://openalex.org/W3205506801","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W4224939635","https://openalex.org/W4292794827"],"abstract_inverted_index":{"Attention":[0,87],"mechanisms,":[1],"which":[2,48,94],"enable":[3,153],"a":[4,126,146],"neural":[5,29],"network":[6],"to":[7,23,50,90,98,129,152],"accurately":[8],"focus":[9],"on":[10,205],"all":[11,141],"the":[12,16,25,52,76,168,175,190,222,226],"relevant":[13],"elements":[14],"of":[15,27,102,172,199],"input,":[17],"have":[18],"become":[19],"an":[20,84],"essential":[21],"component":[22],"improve":[24],"performance":[26,67,191],"deep":[28],"networks.":[30],"There":[31],"are":[32,143,178],"mainly":[33],"two":[34,100],"attention":[35,44,103],"mechanisms":[36,104],"widely":[37],"used":[38],"in":[39,118,133,197],"computer":[40],"vision":[41],"studies,":[42],"spatial":[43,135],"and":[45,56,136,145,170,182,189,217],"channel":[46,57,110,137],"attention,":[47],"aim":[49],"capture":[51],"pixel-level":[53],"pairwise":[54],"relationship":[55],"dependency,":[58],"respectively.":[59],"Although":[60],"fusing":[61],"them":[62,117],"together":[63],"may":[64],"achieve":[65],"better":[66],"than":[68,195],"their":[69],"individual":[70],"implementations,":[71],"it":[72],"will":[73],"inevitably":[74],"increase":[75],"computational":[77],"overhead.":[78],"In":[79],"this":[80,92],"paper,":[81],"we":[82],"propose":[83],"efficient":[85,164],"Shuffle":[86,96,127],"(SA)":[88],"module":[89,162],"address":[91],"issue,":[93],"adopts":[95],"Units":[97],"combine":[99],"types":[101],"effectively.":[105],"Specifically,":[106],"SA":[107,124,161,173,224],"first":[108],"groups":[109],"dimensions":[111],"into":[112],"multiple":[113],"sub-features":[114,142],"before":[115],"processing":[116],"parallel.":[119],"Then,":[120],"for":[121,210,214],"each":[122],"sub-feature,":[123],"utilizes":[125],"Unit":[128],"depict":[130],"feature":[131],"dependencies":[132],"both":[134],"dimensions.":[138],"After":[139],"that,":[140],"aggregated":[144],"\"channel":[147],"shuffle\"":[148],"operator":[149],"is":[150,163,193],"adopted":[151],"information":[154],"communication":[155],"between":[156],"different":[157],"sub-features.":[158],"The":[159],"proposed":[160,223],"yet":[165],"effective,":[166],"e.g.,":[167],"parameters":[169],"computations":[171],"against":[174],"backbone":[176],"ResNet50":[177],"300":[179],"vs.":[180,185],"25.56M":[181],"2.76e-3":[183],"GFLOPs":[184],"4.12":[186],"GFLOPs,":[187],"respectively,":[188],"boost":[192],"more":[194],"1.34%":[196],"terms":[198],"Top-1":[200],"accuracy.":[201],"Extensive":[202],"experimental":[203],"results":[204],"common-used":[206],"benchmarks,":[207],"including":[208],"ImageNet-1k":[209],"classification,":[211],"MS":[212],"COCO":[213],"object":[215],"detection,":[216],"instance":[218],"segmentation,":[219],"demonstrate":[220],"that":[221],"outperforms":[225],"current":[227],"SOTA":[228],"methods":[229],"significantly":[230],"by":[231],"achieving":[232],"higher":[233],"accuracy":[234],"while":[235],"having":[236],"lower":[237],"model":[238],"complexity.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":86},{"year":2025,"cited_by_count":273},{"year":2024,"cited_by_count":301},{"year":2023,"cited_by_count":205},{"year":2022,"cited_by_count":94},{"year":2021,"cited_by_count":26}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}