{"id":"https://openalex.org/W4399766323","doi":"https://doi.org/10.1109/tai.2024.3415551","title":"CS-Mixer: A Cross-Scale Vision Multilayer Perceptron With Spatial\u2013Channel Mixing","display_name":"CS-Mixer: A Cross-Scale Vision Multilayer Perceptron With Spatial\u2013Channel Mixing","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4399766323","doi":"https://doi.org/10.1109/tai.2024.3415551"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2024.3415551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3415551","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-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/A5061777047","display_name":"Jonathan Cui","orcid":"https://orcid.org/0000-0002-5075-3524"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jonathan Cui","raw_affiliation_strings":["Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101381089","display_name":"David A. Araujo","orcid":"https://orcid.org/0009-0008-3321-9195"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David A. Araujo","raw_affiliation_strings":["Pennsylvania State University &#x2013; Harrisburg, Middletown, PA, USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University &#x2013; Harrisburg, Middletown, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114686140","display_name":"Suman Saha","orcid":"https://orcid.org/0009-0005-9440-6785"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suman Saha","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000519641","display_name":"Md Faisal Kabir","orcid":"https://orcid.org/0000-0001-6088-9487"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Faisal Kabir","raw_affiliation_strings":["School of Science, Engineering, and Technology, Pennsylvania State University &#x2013; Harrisburg, Middletown, PA, USA"],"affiliations":[{"raw_affiliation_string":"School of Science, Engineering, and Technology, Pennsylvania State University &#x2013; Harrisburg, Middletown, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061777047"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":1.0911,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80279424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"5","issue":"10","first_page":"4915","last_page":"4927"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9904000163078308,"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":0.9904000163078308,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12676","display_name":"Machine Learning and ELM","score":0.9775999784469604,"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/mixing","display_name":"Mixing (physics)","score":0.6221426129341125},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5577625036239624},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5313803553581238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4625854194164276},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43060046434402466},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.428935706615448},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4127155542373657},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36338478326797485},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.27837058901786804},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.23336172103881836},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.22994664311408997},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.21003907918930054},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.207289457321167},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13408946990966797},{"id":"https://openalex.org/keywords/nanotechnology","display_name":"Nanotechnology","score":0.07925990223884583}],"concepts":[{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.6221426129341125},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5577625036239624},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5313803553581238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4625854194164276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43060046434402466},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.428935706615448},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4127155542373657},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36338478326797485},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.27837058901786804},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.23336172103881836},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.22994664311408997},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.21003907918930054},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.207289457321167},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13408946990966797},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.07925990223884583},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2024.3415551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3415551","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2081580037","https://openalex.org/W2117539524","https://openalex.org/W2331143823","https://openalex.org/W2531409750","https://openalex.org/W2533598788","https://openalex.org/W2601564443","https://openalex.org/W2899663614","https://openalex.org/W2899771611","https://openalex.org/W2963263347","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W3118608800","https://openalex.org/W3137963805","https://openalex.org/W3138516171","https://openalex.org/W3163465952","https://openalex.org/W3172942063","https://openalex.org/W3174699664","https://openalex.org/W3212972574","https://openalex.org/W4212819272","https://openalex.org/W4214633470","https://openalex.org/W4214634256","https://openalex.org/W4221154952","https://openalex.org/W4226297238","https://openalex.org/W4226363321","https://openalex.org/W4312443924","https://openalex.org/W4312820606","https://openalex.org/W4312847199","https://openalex.org/W4313056180","https://openalex.org/W4322096544","https://openalex.org/W4372267514","https://openalex.org/W4385245566","https://openalex.org/W4385815585","https://openalex.org/W4389609834","https://openalex.org/W6684191040","https://openalex.org/W6726497184","https://openalex.org/W6745136726","https://openalex.org/W6755977528","https://openalex.org/W6756040250","https://openalex.org/W6762718338","https://openalex.org/W6771378132","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6787972765","https://openalex.org/W6790428460","https://openalex.org/W6791705549","https://openalex.org/W6795140394","https://openalex.org/W6796417832","https://openalex.org/W6797235774","https://openalex.org/W6799423381","https://openalex.org/W6810093917","https://openalex.org/W6841287799","https://openalex.org/W7075999875"],"related_works":["https://openalex.org/W2082756648","https://openalex.org/W3194278305","https://openalex.org/W2289648981","https://openalex.org/W2373038869","https://openalex.org/W1565459987","https://openalex.org/W2375908649","https://openalex.org/W2614837930","https://openalex.org/W165228748","https://openalex.org/W45198419","https://openalex.org/W2001427828"],"abstract_inverted_index":{"Despite":[0],"simpler":[1],"architectural":[2],"designs":[3],"compared":[4,86],"with":[5,51,87,100,193],"vision":[6,13,45,129],"transformers":[7],"(ViTs)":[8],"and":[9,21,28,37,65,75,111,143,196],"convolutional":[10],"neural":[11],"networks,":[12],"multilayer":[14],"perceptrons":[15],"(MLPs)":[16],"have":[17],"demonstrated":[18],"strong":[19],"performance":[20,85],"high":[22],"data":[23],"efficiency":[24],"for":[25,136,148],"image":[26,175],"classification":[27],"semantic":[29],"segmentation.":[30],"Following":[31],"pioneering":[32],"works":[33],"such":[34,61],"as":[35,62],"MLP-Mixers":[36],"gMLPs,":[38],"later":[39],"research":[40],"proposed":[41,168],"a":[42,127,159],"plethora":[43],"of":[44],"MLP":[46,97,130],"architectures":[47],"that":[48,90,131,150,162],"achieve":[49],"token-mixing":[50,149],"specifically":[52],"engineered":[53],"convolution-":[54],"or":[55,106],"attentionlike":[56],"mechanisms.":[57],"However,":[58],"existing":[59],"methods":[60],"<inline-formula><tex-math":[63],"notation=\"LaTeX\">$\\text{S}^{\\text{2}}$</tex-math></inline-formula>-MLPs":[64],"PoolFormers":[66],"typically":[67],"model":[68,104],"spatial":[69,73,80],"information":[70],"in":[71],"equal-sized":[72],"regions":[74],"do":[76],"not":[77],"consider":[78],"cross-scale":[79],"interactions,":[81,154],"thus":[82],"delivering":[83],"subpar":[84],"transformer":[88],"models":[89,152],"employ":[91],"global":[92],"token":[93],"mixing.":[94],"Further,":[95],"these":[96],"token-mixers,":[98],"along":[99],"most":[101],"ViTs,":[102],"only":[103],"one-":[105],"two-axis":[107],"correlations":[108],"among":[109],"space":[110],"channels,":[112],"avoiding":[113],"simultaneous":[114],"three-axis":[115],"spatial\u2013channel":[116,153],"mixing":[117],"due":[118],"to":[119,164],"its":[120],"computational":[121],"demands.":[122],"We,":[123],"therefore,":[124],"propose":[125],"CS-Mixer,":[126],"hierarchical":[128],"learns":[132],"dynamic":[133],"low-rank":[134],"transformations":[135],"tokens":[137],"aggregated":[138],"across":[139],"scales,":[140],"both":[141],"locally":[142],"globally.":[144],"Such":[145],"aggregation":[146],"allows":[147],"explicitly":[151],"made":[155],"computationally":[156],"possible":[157],"by":[158],"multihead":[160],"design":[161],"projects":[163],"low-dimensional":[165],"subspaces.":[166],"The":[167],"methodology":[169],"achieves":[170],"competitive":[171],"results":[172],"on":[173,191],"popular":[174],"recognition":[176],"benchmarks":[177],"without":[178],"incurring":[179],"substantially":[180],"more":[181],"computing.":[182],"Our":[183],"largest":[184],"model,":[185],"CS-Mixer-L,":[186],"reaches":[187],"83.2%":[188],"top-1":[189],"accuracy":[190],"ImageNet-1k":[192],"13.7":[194],"GFLOPs":[195],"94":[197],"M":[198],"parameters.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}