{"id":"https://openalex.org/W4415202911","doi":"https://doi.org/10.1109/iccv51701.2025.02100","title":"Frequency-Dynamic Attention Modulation for Dense Prediction","display_name":"Frequency-Dynamic Attention Modulation for Dense Prediction","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415202911","doi":"https://doi.org/10.1109/iccv51701.2025.02100"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02100","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.12006","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101966357","display_name":"Linwei Chen","orcid":"https://orcid.org/0000-0003-3676-7812"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linwei Chen","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016680184","display_name":"Lin Gu","orcid":"https://orcid.org/0000-0002-7504-031X"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lin Gu","raw_affiliation_strings":["RIKEN AIP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN AIP","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102012777","display_name":"Ying Fu","orcid":"https://orcid.org/0000-0002-2442-1809"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Fu","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101966357"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14282742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22620","last_page":"22632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9448999762535095,"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":0.9448999762535095,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9261999726295471,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/transformer","display_name":"Transformer","score":0.5551999807357788},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4424999952316284},{"id":"https://openalex.org/keywords/frequency-response","display_name":"Frequency response","score":0.4162999987602234},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.4032999873161316},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3928999900817871},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.34549999237060547},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.31130000948905945},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3082999885082245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124000191688538},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5551999807357788},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.4494999945163727},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41990000009536743},{"id":"https://openalex.org/C8590192","wikidata":"https://www.wikidata.org/wiki/Q1054694","display_name":"Frequency response","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.4032999873161316},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3928999900817871},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.3075999915599823},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29490000009536743},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C36390408","wikidata":"https://www.wikidata.org/wiki/Q1163067","display_name":"Digital filter","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C22597639","wikidata":"https://www.wikidata.org/wiki/Q5449227","display_name":"Filter design","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C140101238","wikidata":"https://www.wikidata.org/wiki/Q1404885","display_name":"Window function","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02100","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:2507.12006","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12006","pdf_url":"https://arxiv.org/pdf/2507.12006","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.12006","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.12006","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.12006","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12006","pdf_url":"https://arxiv.org/pdf/2507.12006","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1528331741","display_name":null,"funder_award_id":"62331006,62171038,62088101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3056003011","display_name":null,"funder_award_id":"JPMJMS2011","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"},{"id":"https://openalex.org/G4515895501","display_name":null,"funder_award_id":"2022YFC3300705","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision":[0],"Transformers":[1],"(ViTs)":[2],"have":[3],"significantly":[4],"advanced":[5],"computer":[6],"vision,":[7],"demonstrating":[8],"strong":[9],"performance":[10,158],"across":[11,160],"various":[12,161],"tasks.":[13],"However,":[14],"the":[15,29,42,70,110,114,120,135],"attention":[16,115],"mechanism":[17],"in":[18,32,113,172,195],"ViTs":[19,75],"makes":[20],"each":[21],"layer":[22],"function":[23],"as":[24,95,175],"a":[25,51,101],"low-pass":[26,93,111],"filter,":[27],"and":[28,47,76,84,117,143,166,180],"stacked-layer":[30],"architecture":[31],"existing":[33],"transformers":[34],"suffers":[35],"from":[36],"frequency":[37,72,129],"vanishing.":[38],"This":[39],"leads":[40],"to":[41,126,134,156,188],"loss":[43],"of":[44,74,78],"critical":[45],"details":[46],"textures.":[48],"We":[49,122],"propose":[50],"novel,":[52],"circuit-theory-inspired":[53],"strategy":[54],"called":[55],"Frequency-Dynamic":[56],"Attention":[57,81],"Modulation":[58],"(FDAM),":[59],"which":[60],"can":[61],"be":[62],"easily":[63],"plugged":[64],"into":[65],"ViTs.":[66],"FDAM":[67],"directly":[68],"modulates":[69],"overall":[71],"response":[73,137],"consists":[77],"two":[79],"techniques:":[80],"Inversion":[82],"(AttInv)":[83],"Frequency":[85],"Dynamic":[86],"Scaling":[87],"(FreqScale).":[88],"Since":[89],"circuit":[90],"theory":[91],"uses":[92],"filters":[94],"fundamental":[96],"elements,":[97],"we":[98,147,184],"introduce":[99],"AttInv,":[100],"method":[102,187],"that":[103,149],"generates":[104],"complementary":[105],"high-pass":[106],"filtering":[107],"by":[108],"inverting":[109],"filter":[112],"matrix,":[116],"dynamically":[118],"combining":[119],"two.":[121],"further":[123],"design":[124],"FreqScale":[125],"weight":[127],"different":[128],"components":[130],"for":[131],"fine-grained":[132],"adjustments":[133],"target":[136],"function.":[138],"Through":[139],"feature":[140],"similarity":[141],"analysis":[142],"effective":[144],"rank":[145],"evaluation,":[146],"demonstrate":[148],"our":[150,186],"approach":[151],"avoids":[152],"representation":[153],"collapse,":[154],"leading":[155],"consistent":[157],"improvements":[159,169],"models,":[162],"including":[163],"SegFormer,":[164],"DeiT,":[165],"MaskDINO.":[167],"These":[168],"are":[170],"evident":[171],"tasks":[173],"such":[174],"semantic":[176],"segmentation,":[177],"object":[178],"detection,":[179,191],"instance":[181],"segmentation.":[182],"Additionally,":[183],"apply":[185],"remote":[189],"sensing":[190],"achieving":[192],"state-of-the-art":[193],"results":[194],"single-scale":[196],"settings.":[197],"The":[198],"code":[199],"is":[200],"available":[201],"at":[202],"https://github.com/Linwei-Chen/FDAM.":[203]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-16T00:00:00"}