{"id":"https://openalex.org/W4372260325","doi":"https://doi.org/10.1109/icassp49357.2023.10097256","title":"DMFormer: Closing the gap Between CNN and Vision Transformers","display_name":"DMFormer: Closing the gap Between CNN and Vision Transformers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260325","doi":"https://doi.org/10.1109/icassp49357.2023.10097256"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5016625901","display_name":"Zimian Wei","orcid":"https://orcid.org/0000-0002-9524-116X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zimian Wei","raw_affiliation_strings":["National University of Defense Technology,College of Computer","College of Computer, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053995594","display_name":"Hengyue Pan","orcid":"https://orcid.org/0000-0002-2999-7401"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengyue Pan","raw_affiliation_strings":["National University of Defense Technology,College of Computer","College of Computer, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115601450","display_name":"Lujun Li","orcid":"https://orcid.org/0000-0001-9114-4525"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lujun Li","raw_affiliation_strings":["Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091320085","display_name":"Menglong Lu","orcid":"https://orcid.org/0000-0003-0011-0368"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menglong Lu","raw_affiliation_strings":["National University of Defense Technology,College of Computer","College of Computer, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103127264","display_name":"Xin Niu","orcid":"https://orcid.org/0000-0002-4173-0822"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Niu","raw_affiliation_strings":["National University of Defense Technology,College of Computer","College of Computer, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010390403","display_name":"Peijie Dong","orcid":"https://orcid.org/0000-0003-1952-4544"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peijie Dong","raw_affiliation_strings":["National University of Defense Technology,College of Computer","College of Computer, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["National University of Defense Technology,College of Computer","College of Computer, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5016625901"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.9839,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7717217,"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":"1","last_page":"5"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9994000196456909,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7795702219009399},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6764038801193237},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6659218668937683},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5796446204185486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5693759322166443},{"id":"https://openalex.org/keywords/closing","display_name":"Closing (real estate)","score":0.447465717792511},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.427884578704834},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34602946043014526},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14233049750328064},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13602957129478455},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12480169534683228},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08553105592727661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795702219009399},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6764038801193237},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6659218668937683},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5796446204185486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5693759322166443},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.447465717792511},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.427884578704834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34602946043014526},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14233049750328064},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13602957129478455},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12480169534683228},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08553105592727661},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2737258237","https://openalex.org/W2884822772","https://openalex.org/W2899663614","https://openalex.org/W2910628332","https://openalex.org/W2962858109","https://openalex.org/W2963037463","https://openalex.org/W3034429256","https://openalex.org/W3094502228","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3157528469","https://openalex.org/W3168101492","https://openalex.org/W3170874841","https://openalex.org/W3175515048","https://openalex.org/W3176153963","https://openalex.org/W4226334005","https://openalex.org/W4287122968","https://openalex.org/W4312443924","https://openalex.org/W4312820606","https://openalex.org/W4385346076","https://openalex.org/W6753421600","https://openalex.org/W6755977528","https://openalex.org/W6766029800","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6794345597","https://openalex.org/W6796237581","https://openalex.org/W6797533734","https://openalex.org/W6798016242","https://openalex.org/W6809468216","https://openalex.org/W6811173682","https://openalex.org/W6839818334"],"related_works":["https://openalex.org/W2517007886","https://openalex.org/W2383994331","https://openalex.org/W1522019333","https://openalex.org/W3121919567","https://openalex.org/W2076369646","https://openalex.org/W278047738","https://openalex.org/W2373884197","https://openalex.org/W4244817184","https://openalex.org/W2516969888","https://openalex.org/W2249653223"],"abstract_inverted_index":{"Vision":[0],"transformers":[1,30],"have":[2],"shown":[3],"excellent":[4],"performance":[5],"in":[6,28],"computer":[7],"vision":[8,29,104,132],"tasks.":[9],"As":[10],"the":[11,25,100,108],"computation":[12],"cost":[13],"of":[14,72,103],"their":[15],"self-attention":[16,26,109],"mechanism":[17,27,66,110],"is":[18,35],"expensive,":[19],"recent":[20],"works":[21],"tried":[22],"to":[23,54],"replace":[24],"with":[31,38,83,111],"convolutional":[32,135],"operations,":[33],"which":[34,68,129],"more":[36],"efficient":[37,93],"built-in":[39],"inductive":[40],"bias.":[41],"However,":[42],"these":[43],"efforts":[44],"either":[45],"ignore":[46],"multi-level":[47],"features":[48],"or":[49],"lack":[50],"dynamic":[51],"prosperity,":[52],"leading":[53],"sub-optimal":[55],"performance.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,90],"propose":[61],"a":[62,84],"Dynamic":[63],"Multi-level":[64],"Attention":[65],"(DMA),":[67],"captures":[69],"different":[70],"patterns":[71],"input":[73],"images":[74],"by":[75],"multiple":[76],"kernel":[77],"sizes":[78],"and":[79,120,134],"enables":[80],"input-adaptive":[81],"weights":[82],"gating":[85],"mechanism.":[86],"Based":[87],"on":[88,118],"DMA,":[89],"present":[91],"an":[92],"backbone":[94],"network":[95],"named":[96],"DMFormer.":[97],"DMFormer":[98,125],"adopts":[99],"overall":[101],"architecture":[102],"transformers,":[105],"while":[106],"replacing":[107],"our":[112],"proposed":[113],"DMA.":[114],"Extensive":[115],"experimental":[116],"results":[117],"ImageNet-1K":[119],"ADE20K":[121],"datasets":[122],"demonstrated":[123],"that":[124],"achieves":[126],"state-of-the-art":[127],"performance,":[128],"outperforms":[130],"similar-sized":[131],"transformers(ViTs)":[133],"neural":[136],"networks":[137],"(CNNs).":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}