{"id":"https://openalex.org/W4385764523","doi":"https://doi.org/10.24963/ijcai.2023/111","title":"RaMLP: Vision MLP via Region-aware Mixing","display_name":"RaMLP: Vision MLP via Region-aware Mixing","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764523","doi":"https://doi.org/10.24963/ijcai.2023/111"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/111","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/111","pdf_url":"https://www.ijcai.org/proceedings/2023/0111.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0111.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101685414","display_name":"Shenqi Lai","orcid":"https://orcid.org/0000-0001-8673-2218"},"institutions":[{"id":"https://openalex.org/I4210099567","display_name":"Insight (China)","ror":"https://ror.org/010t34638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099567"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenqi Lai","raw_affiliation_strings":["InsightFace.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InsightFace.ai","institution_ids":["https://openalex.org/I4210099567"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671248","display_name":"Xi Du","orcid":"https://orcid.org/0000-0002-1207-6219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi Du","raw_affiliation_strings":["Kiwi Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kiwi Tech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028623085","display_name":"Jia Guo","orcid":"https://orcid.org/0000-0002-0709-261X"},"institutions":[{"id":"https://openalex.org/I4210099567","display_name":"Insight (China)","ror":"https://ror.org/010t34638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099567"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Guo","raw_affiliation_strings":["InsightFace.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InsightFace.ai","institution_ids":["https://openalex.org/I4210099567"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036606244","display_name":"Kaipeng Zhang","orcid":"https://orcid.org/0000-0001-6105-6532"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaipeng Zhang","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8109,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81149316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"999","last_page":"1007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987000226974487,"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":0.9979000091552734,"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":0.8657987117767334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.694880485534668},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6162833571434021},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6075185537338257},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5696932077407837},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5668609738349915},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5622569918632507},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5006511211395264},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4869895875453949},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4729616045951843},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46125921607017517},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4554942548274994},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4543728530406952},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4238879084587097},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3391599953174591},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2981697916984558},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.19217842817306519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8657987117767334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.694880485534668},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6162833571434021},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6075185537338257},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5696932077407837},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5668609738349915},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5622569918632507},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5006511211395264},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4869895875453949},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4729616045951843},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46125921607017517},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4554942548274994},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4543728530406952},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4238879084587097},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3391599953174591},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2981697916984558},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.19217842817306519},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/111","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/111","pdf_url":"https://www.ijcai.org/proceedings/2023/0111.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/111","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/111","pdf_url":"https://www.ijcai.org/proceedings/2023/0111.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.6200000047683716,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764523.pdf","grobid_xml":"https://content.openalex.org/works/W4385764523.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1861492603","https://openalex.org/W2097117768","https://openalex.org/W2163605009","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2507296351","https://openalex.org/W2884561390","https://openalex.org/W2896457183","https://openalex.org/W2910628332","https://openalex.org/W2964350391","https://openalex.org/W3094502228","https://openalex.org/W3121523901","https://openalex.org/W3138516171","https://openalex.org/W3139049060","https://openalex.org/W3156811085","https://openalex.org/W3157506437","https://openalex.org/W3157528469","https://openalex.org/W3163465952","https://openalex.org/W3170874841","https://openalex.org/W3183804933","https://openalex.org/W3213783001","https://openalex.org/W4214493665","https://openalex.org/W4221154675","https://openalex.org/W4226028923","https://openalex.org/W4226363321","https://openalex.org/W4226483979","https://openalex.org/W4239072543","https://openalex.org/W4287073339","https://openalex.org/W4287324101","https://openalex.org/W4292779060","https://openalex.org/W4293680532","https://openalex.org/W4297575730","https://openalex.org/W4302275239","https://openalex.org/W4313007769"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W2340870721","https://openalex.org/W2358318464","https://openalex.org/W2979236518","https://openalex.org/W3091955004"],"abstract_inverted_index":{"Recently,":[0],"MLP-based":[1,80,139],"architectures":[2,140],"achieved":[3],"impressive":[4],"results":[5],"in":[6,19,128],"image":[7,26,34,174],"classification":[8,175],"against":[9],"CNNs":[10],"and":[11,47,90,111,153,169,176,188],"ViTs.":[12],"However,":[13],"there":[14],"is":[15,132,151],"an":[16],"obvious":[17],"limitation":[18],"that":[20,141],"their":[21],"parameters":[22],"are":[23,52,73],"related":[24],"to":[25,30,59,85,147,157],"sizes,":[27],"allowing":[28],"them":[29],"process":[31],"only":[32],"fixed":[33],"sizes.":[35,55],"Therefore,":[36],"they":[37],"cannot":[38],"directly":[39],"adapt":[40],"dense":[41,178,208],"prediction":[42,179,209],"tasks":[43,89],"(e.g.,":[44],"object":[45,183],"detection":[46],"semantic":[48,190],"segmentation)":[49],"where":[50],"images":[51],"of":[53],"various":[54,87],"Recent":[56],"methods":[57],"tried":[58],"address":[60,91],"it":[61],"but":[62],"brought":[63],"two":[64],"new":[65,79],"problems,":[66],"long-range":[67],"dependencies":[68],"or":[69,204],"important":[70,108,115],"visual":[71,116],"cues":[72],"ignored.":[74],"This":[75],"paper":[76],"presents":[77],"a":[78,100,123,198],"architecture,":[81],"Region-aware":[82,103],"MLP":[83],"(RaMLP),":[84],"satisfy":[86],"vision":[88],"the":[92,143],"above":[93],"three":[94],"problems.":[95],"In":[96,192],"particular,":[97,193],"we":[98],"propose":[99],"well-designed":[101],"module,":[102],"Mixing":[104],"(RaM).":[105],"RaM":[106,150],"captures":[107],"local":[109],"information":[110],"further":[112],"aggregates":[113],"these":[114],"clues.":[117],"Based":[118],"on":[119,171,207],"RaM,":[120],"RaMLP":[121,164,194],"achieves":[122],"global":[124],"receptive":[125],"field":[126],"even":[127],"one":[129],"block.":[130],"It":[131],"worth":[133],"noting":[134],"that,":[135],"unlike":[136],"most":[137],"existing":[138],"adopt":[142],"same":[144],"spatial":[145],"weights":[146,156],"all":[148],"samples,":[149],"region-aware":[152],"adaptively":[154],"determines":[155],"extract":[158],"region-level":[159],"features":[160],"better.":[161],"Impressively,":[162],"our":[163],"outperforms":[165,195],"state-of-the-art":[166],"ViTs,":[167],"CNNs,":[168],"MLPs":[170,196],"both":[172],"ImageNet-1K":[173],"downstream":[177],"tasks,":[180],"including":[181],"MS-COCO":[182,185],"detection,":[184],"instance":[186],"segmentation,":[187],"ADE20K":[189],"segmentation.":[191],"by":[197],"large":[199],"margin":[200],"(around":[201],"1.5%":[202],"Apb":[203],"1.0%":[205],"mIoU)":[206],"tasks.":[210],"The":[211],"training":[212],"code":[213],"could":[214],"be":[215],"found":[216],"at":[217],"https://github.com/xiaolai-sqlai/RaMLP.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}