{"id":"https://openalex.org/W4404988812","doi":"https://doi.org/10.1109/iccv51701.2025.02183","title":"TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba","display_name":"TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404988812","doi":"https://doi.org/10.1109/iccv51701.2025.02183"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.17473","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000379252","display_name":"Xiaowen Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xiaowen Ma","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319349","display_name":"Zhipeng Ni","orcid":"https://orcid.org/0000-0003-0965-1398"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zhenliang Ni","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xinghao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xinghao Chen","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159102"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23519","last_page":"23529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9277999997138977,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9277999997138977,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9049000144004822,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10531","display_name":"Advanced Vision and Imaging","score":0.9035000205039978,"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/decoupling","display_name":"Decoupling (probability)","score":0.8531597852706909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3563733696937561},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14050811529159546},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.09422138333320618}],"concepts":[{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.8531597852706909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3563733696937561},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14050811529159546},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.09422138333320618}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.17473","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.17473","pdf_url":"https://arxiv.org/pdf/2411.17473","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.2411.17473","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.17473","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":"pmh:oai:arXiv.org:2411.17473","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.17473","pdf_url":"https://arxiv.org/pdf/2411.17473","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4313561376","https://openalex.org/W3103825105","https://openalex.org/W3027880158","https://openalex.org/W3207533102","https://openalex.org/W1617565119","https://openalex.org/W160381218","https://openalex.org/W2512958550"],"abstract_inverted_index":{"Mamba":[0,78,114,183],"has":[1],"shown":[2],"great":[3],"potential":[4,59],"for":[5,128],"computer":[6],"vision":[7,61,182],"due":[8],"to":[9,20,55,98,156],"its":[10],"linear":[11],"complexity":[12],"in":[13,48,102],"modeling":[14],"the":[15,21,45,49,58,77,90,100,109,113,119,122,125,147,151,159,219],"global":[16,133],"context":[17],"with":[18,215],"respect":[19],"input":[22,107,148],"length.":[23],"However,":[24],"existing":[25],"lightweight":[26],"Mamba-based":[27,213,230],"backbones":[28],"cannot":[29],"demonstrate":[30],"performance":[31,191],"that":[32,42,76,227],"matches":[33],"Convolution":[34],"or":[35],"Transformer-based":[36],"methods.":[37],"By":[38,167],"observing,":[39],"we":[40,66,92,138,175],"find":[41],"simply":[43],"modifying":[44],"scanning":[46],"path":[47],"image":[50,197],"domain":[51],"is":[52,221,233],"not":[53],"conducive":[54],"fully":[56],"exploiting":[57],"of":[60,104,121,150,179,228],"Mamba.":[62],"In":[63,116,206],"this":[64],"paper,":[65],"first":[67],"perform":[68],"comprehensive":[69],"spectral":[70],"and":[71,74,106,124,131,161,171,203,212,218],"quantitative":[72],"analyses,":[73,91],"verify":[75],"block":[79],"mainly":[80],"models":[81,214],"low-frequency":[82,110,132,162],"information":[83,134],"under":[84],"Convolution-Mamba":[85],"hybrid":[86,181],"architecture.":[87],"Based":[88],"on":[89,192],"introduce":[93,139],"a":[94,140,177],"novel":[95],"Laplace":[96,173],"mixer":[97],"decouple":[99],"features":[101,123],"terms":[103],"frequency":[105,141],"only":[108],"components":[111,163],"into":[112],"block.":[115],"addition,":[117],"considering":[118],"redundancy":[120],"different":[126,136,165],"requirements":[127],"high-frequency":[129,152,160],"details":[130],"at":[135,164,235],"stages,":[137],"ramp":[142],"inception,":[143],"i.e.,":[144],"gradually":[145],"reduce":[146],"dimensions":[149],"branches,":[153],"so":[154],"as":[155],"efficiently":[157],"trade-off":[158],"layers.":[166],"integrating":[168],"mobile-friendly":[169],"convolution":[170],"efficient":[172],"mixer,":[174],"build":[176],"series":[178],"tiny":[180],"called":[184],"TinyViM.":[185],"The":[186],"proposed":[187],"TinyViM":[188,208],"achieves":[189],"impressive":[190],"several":[193],"downstream":[194],"tasks":[195],"including":[196],"classification,":[198],"semantic":[199],"segmentation,":[200],"object":[201],"detection":[202],"instance":[204],"segmentation.":[205],"particular,":[207],"outperforms":[209],"Convolution,":[210],"Transformer":[211],"similar":[216],"scales,":[217],"throughput":[220],"about":[222],"2-3":[223],"times":[224],"higher":[225],"than":[226],"other":[229],"models.":[231],"Code":[232],"available":[234],"https://github.com/xwmaxwma/TinyViM.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}