{"id":"https://openalex.org/W2981408784","doi":"https://doi.org/10.1109/iccv.2019.00194","title":"SRM: A Style-Based Recalibration Module for Convolutional Neural Networks","display_name":"SRM: A Style-Based Recalibration Module for Convolutional Neural Networks","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2981408784","doi":"https://doi.org/10.1109/iccv.2019.00194","mag":"2981408784"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2019.00194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","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/A5100768427","display_name":"Hyunjae Lee","orcid":"https://orcid.org/0000-0002-0569-7383"},"institutions":[{"id":"https://openalex.org/I4210103693","display_name":"Lutron Electronics (United States)","ror":"https://ror.org/01e55bn36","country_code":"US","type":"company","lineage":["https://openalex.org/I4210103693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyunjae Lee","raw_affiliation_strings":["Lunit Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lunit Inc","institution_ids":["https://openalex.org/I4210103693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032400251","display_name":"Hyoeun Kim","orcid":"https://orcid.org/0000-0002-7334-9700"},"institutions":[{"id":"https://openalex.org/I4210103693","display_name":"Lutron Electronics (United States)","ror":"https://ror.org/01e55bn36","country_code":"US","type":"company","lineage":["https://openalex.org/I4210103693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyo-Eun Kim","raw_affiliation_strings":["Lunit Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lunit Inc","institution_ids":["https://openalex.org/I4210103693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018432453","display_name":"Hyeonseob Nam","orcid":"https://orcid.org/0000-0002-0375-0080"},"institutions":[{"id":"https://openalex.org/I4210103693","display_name":"Lutron Electronics (United States)","ror":"https://ror.org/01e55bn36","country_code":"US","type":"company","lineage":["https://openalex.org/I4210103693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyeonseob Nam","raw_affiliation_strings":["Lunit Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lunit Inc","institution_ids":["https://openalex.org/I4210103693"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210103693"],"apc_list":null,"apc_paid":null,"fwci":7.4826,"has_fulltext":false,"cited_by_count":330,"citation_normalized_percentile":{"value":0.97580113,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1854","last_page":"1862"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.998199999332428,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.994700014591217,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7950485348701477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7278426289558411},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7020584940910339},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6625233888626099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5206750631332397},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5043939352035522},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48160144686698914},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.41526445746421814},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36530742049217224}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7950485348701477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278426289558411},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7020584940910339},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6625233888626099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5206750631332397},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5043939352035522},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48160144686698914},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.41526445746421814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36530742049217224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv.2019.00194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.5600000023841858,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W819977924","https://openalex.org/W1514535095","https://openalex.org/W1836465849","https://openalex.org/W1861492603","https://openalex.org/W2019370496","https://openalex.org/W2047643928","https://openalex.org/W2117539524","https://openalex.org/W2122710056","https://openalex.org/W2128272608","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2331128040","https://openalex.org/W2412782625","https://openalex.org/W2475287302","https://openalex.org/W2502312327","https://openalex.org/W2546696630","https://openalex.org/W2572730214","https://openalex.org/W2583638424","https://openalex.org/W2593768305","https://openalex.org/W2603777577","https://openalex.org/W2627183927","https://openalex.org/W2752782242","https://openalex.org/W2803808038","https://openalex.org/W2884585870","https://openalex.org/W2898732869","https://openalex.org/W2902617128","https://openalex.org/W2910992787","https://openalex.org/W2952865063","https://openalex.org/W2962770929","https://openalex.org/W2962808524","https://openalex.org/W2962839335","https://openalex.org/W2963091558","https://openalex.org/W2963211188","https://openalex.org/W2963420686","https://openalex.org/W2963495494","https://openalex.org/W2963984455","https://openalex.org/W2964193438","https://openalex.org/W3106250896","https://openalex.org/W3118608800","https://openalex.org/W4297772692","https://openalex.org/W4308831279","https://openalex.org/W6618372016","https://openalex.org/W6630875275","https://openalex.org/W6638667902","https://openalex.org/W6639102338","https://openalex.org/W6678174250","https://openalex.org/W6683590716","https://openalex.org/W6684191040","https://openalex.org/W6715287400","https://openalex.org/W6724804524","https://openalex.org/W6738045163","https://openalex.org/W6746282794","https://openalex.org/W6751546485","https://openalex.org/W6756444276","https://openalex.org/W6757146666","https://openalex.org/W6758132781","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W147410782","https://openalex.org/W3022252430","https://openalex.org/W3103989898","https://openalex.org/W4287804464","https://openalex.org/W803346624","https://openalex.org/W2152352598","https://openalex.org/W2810679507"],"abstract_inverted_index":{"Following":[0],"the":[1,11,33,39,73,80,97,109,145,158],"advance":[2],"of":[3,13,35,41,79,100,112,147,170],"style":[4,74,84,93],"transfer":[5],"with":[6,125],"Convolutional":[7],"Neural":[8],"Networks":[9],"(CNNs),":[10],"role":[12],"styles":[14,36,102],"in":[15,43],"CNNs":[16,42],"has":[17],"drawn":[18],"growing":[19],"attention":[20],"from":[21,76],"a":[22,49,54,113],"broader":[23],"perspective.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,165],"aim":[29],"to":[30,37,141],"fully":[31],"leverage":[32],"potential":[34],"improve":[38],"performance":[40],"general":[44,133],"vision":[45],"tasks.":[46],"We":[47,128],"propose":[48],"Style-based":[50],"Recalibration":[51],"Module":[52],"(SRM),":[53],"simple":[55],"yet":[56],"effective":[57],"architectural":[58],"unit,":[59],"which":[60,143],"adaptively":[61],"recalibrates":[62],"intermediate":[63],"feature":[64,81,104],"maps":[65,82],"by":[66,83],"exploiting":[67],"their":[68,171],"styles.":[69],"SRM":[70,106,148,162],"first":[71],"extracts":[72],"information":[75],"each":[77],"channel":[78],"pooling,":[85],"then":[86],"estimates":[87],"per-channel":[88],"recalibration":[89],"weight":[90],"via":[91],"channel-independent":[92],"integration.":[94],"By":[95],"incorporating":[96],"relative":[98],"importance":[99],"individual":[101],"into":[103,121],"maps,":[105],"effectively":[107],"enhances":[108],"representational":[110,172],"ability":[111],"CNN.":[114],"The":[115],"proposed":[116],"module":[117],"is":[118],"directly":[119],"fed":[120],"existing":[122],"CNN":[123],"architectures":[124],"negligible":[126],"overhead.":[127],"conduct":[129],"comprehensive":[130],"experiments":[131],"on":[132],"image":[134],"recognition":[135],"as":[136,138,153],"well":[137],"tasks":[139],"related":[140],"styles,":[142],"verify":[144],"benefit":[146],"over":[149],"recent":[150],"approaches":[151],"such":[152],"Squeeze-and-Excitation":[154],"(SE).":[155],"To":[156],"explain":[157],"inherent":[159],"difference":[160],"between":[161],"and":[163],"SE,":[164],"provide":[166],"an":[167],"in-depth":[168],"comparison":[169],"properties.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":63},{"year":2024,"cited_by_count":80},{"year":2023,"cited_by_count":82},{"year":2022,"cited_by_count":42},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}