{"id":"https://openalex.org/W4413144865","doi":"https://doi.org/10.1109/cvpr52734.2025.02809","title":"Frequency Dynamic Convolution for Dense Image Prediction","display_name":"Frequency Dynamic Convolution for Dense Image Prediction","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144865","doi":"https://doi.org/10.1109/cvpr52734.2025.02809"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.02809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5076356236","display_name":"Linwei Chen","orcid":"https://orcid.org/0000-0002-9639-3237"},"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":"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/A5101553857","display_name":"Lin Gu","orcid":"https://orcid.org/0000-0001-9269-7092"},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lin Gu","raw_affiliation_strings":["RIKEN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RIKEN","institution_ids":["https://openalex.org/I4210110652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420741","display_name":"Liang Li","orcid":"https://orcid.org/0009-0009-2440-2905"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055635944","display_name":"Chenggang Yan","orcid":"https://orcid.org/0000-0001-5957-3207"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenggang Yan","raw_affiliation_strings":["Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100738025","display_name":"Ying Fu","orcid":"https://orcid.org/0000-0002-6677-694X"},"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":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":97.8896,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.99976196,"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":"30178","last_page":"30188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.847000002861023,"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":0.847000002861023,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.833899974822998,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.7192000150680542,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6994884014129639},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6337407827377319},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5187997221946716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4375873804092407},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3882829546928406},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1268346905708313}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6994884014129639},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6337407827377319},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5187997221946716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4375873804092407},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3882829546928406},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1268346905708313}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.02809","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.02809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":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/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"While":[0],"Dynamic":[1,47],"Convolution":[2,48],"(DY-Conv)":[3],"has":[4],"shown":[5],"promising":[6],"performance":[7,160],"by":[8,57],"enabling":[9,78],"adaptive":[10],"weight":[11],"selection":[12],"through":[13],"multiple":[14],"parallel":[15],"weights":[16,27,83,120],"combined":[17],"with":[18,74,161],"an":[19],"attention":[20],"mechanism,":[21],"the":[22,64,79,86,107,114,126,146],"frequency":[23,108,123,127],"response":[24,109],"of":[25,81,110,148,165,190],"these":[26,55],"tends":[28],"to":[29,155],"exhibit":[30],"high":[31,35],"similarity,":[32],"resulting":[33],"in":[34,63,125,175],"parameter":[36,61,87,176],"costs":[37],"but":[38],"limited":[39],"adaptability.":[40],"In":[41],"this":[42,69],"work,":[43],"we":[44,93],"introduce":[45],"Frequency":[46,100],"(FDConv),":[49],"a":[50,59,162,188,196],"novel":[51],"approach":[52],"that":[53,152,171],"mitigates":[54],"limitations":[56],"learning":[58],"fixed":[60],"budget":[62,70],"Fourier":[65,76],"domain.":[66],"FDConv":[67,157],"divides":[68],"into":[71,121,187],"frequency-based":[72],"groups":[73],"disjoint":[75],"indices,":[77],"construction":[80],"frequency-diverse":[82],"without":[84],"increasing":[85],"cost.":[88],"To":[89],"further":[90],"enhance":[91],"adaptability,":[92],"propose":[94],"Kernel":[95],"Spatial":[96],"Modulation":[97,102],"(KSM)":[98],"and":[99,129,143,198],"Band":[101],"(FBM).":[103],"KSM":[104],"dynamically":[105,132],"adjusts":[106],"each":[111],"filter":[112],"at":[113,211],"spatial":[115],"level,":[116],"while":[117],"FBM":[118],"decomposes":[119],"distinct":[122],"bands":[124],"domain":[128],"modulates":[130],"them":[131],"based":[133],"on":[134,139],"local":[135],"content.":[136],"Extensive":[137],"experiments":[138],"object":[140],"detection,":[141],"segmentation,":[142],"classification":[144],"validate":[145],"effectiveness":[147],"FD-Conv.":[149],"We":[150],"demonstrate":[151],"when":[153],"applied":[154],"ResNet-50,":[156],"achieves":[158],"superior":[159],"modest":[163],"increase":[164],"+3.6M":[166],"parameters,":[167],"outperforming":[168],"previous":[169],"methods":[170],"require":[172],"substantial":[173],"increases":[174],"budgets":[177],"(e.g.,":[178],"CondConv":[179],"+90M,":[180],"KW":[181],"+76.5M).":[182],"Moreover,":[183],"FD-Conv":[184],"seamlessly":[185],"integrates":[186],"variety":[189],"architectures,":[191],"including":[192],"ConvNeXt,":[193],"Swin-Transformer,":[194],"offering":[195],"flexible":[197],"efficient":[199],"solution":[200],"for":[201],"modern":[202],"vision":[203],"tasks.":[204],"The":[205],"code":[206],"is":[207],"made":[208],"publicly":[209],"available":[210],"https://github.com/Linwei-Chen/FDConv.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":36},{"year":2025,"cited_by_count":23}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}