{"id":"https://openalex.org/W4312608826","doi":"https://doi.org/10.1109/icpr56361.2022.9956386","title":"Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks","display_name":"Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312608826","doi":"https://doi.org/10.1109/icpr56361.2022.9956386"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956386","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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/A5039687466","display_name":"Yuhuang Hu","orcid":"https://orcid.org/0000-0002-5543-7619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhuang Hu","raw_affiliation_strings":["University of Zürich and ETH Zürich,Institute of Neuroinformatics,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zürich and ETH Zürich,Institute of Neuroinformatics,Switzerland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053821067","display_name":"Shih\u2010Chii Liu","orcid":"https://orcid.org/0000-0002-7557-045X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shih-Chii Liu","raw_affiliation_strings":["University of Zürich and ETH Zürich,Institute of Neuroinformatics,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Zürich and ETH Zürich,Institute of Neuroinformatics,Switzerland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1687,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44810728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2192","last_page":"2198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":1.0,"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/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/T12676","display_name":"Machine Learning and ELM","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8399697542190552},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7042121887207031},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6653976440429688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5984277129173279},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5972163677215576},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5512708425521851},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.525359570980072},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.516576886177063},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5056979656219482},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4454280138015747},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0712510347366333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8399697542190552},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7042121887207031},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6653976440429688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5984277129173279},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5972163677215576},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5512708425521851},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.525359570980072},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.516576886177063},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5056979656219482},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4454280138015747},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0712510347366333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956386","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.7300000190734863,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1836465849","https://openalex.org/W1846799578","https://openalex.org/W2108598243","https://openalex.org/W2125930537","https://openalex.org/W2138011018","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2401823607","https://openalex.org/W2533598788","https://openalex.org/W2604763608","https://openalex.org/W2753160622","https://openalex.org/W2775079417","https://openalex.org/W2798381792","https://openalex.org/W2804935296","https://openalex.org/W2883780447","https://openalex.org/W2898200114","https://openalex.org/W2913190747","https://openalex.org/W2963477238","https://openalex.org/W2982083293","https://openalex.org/W2994749257","https://openalex.org/W2995049146","https://openalex.org/W3007700590","https://openalex.org/W3012561096","https://openalex.org/W3034971973","https://openalex.org/W3098042335","https://openalex.org/W3113151582","https://openalex.org/W3118608800","https://openalex.org/W4250482878","https://openalex.org/W4294375521","https://openalex.org/W6638667902","https://openalex.org/W6638677478","https://openalex.org/W6678818196","https://openalex.org/W6682778277","https://openalex.org/W6684191040","https://openalex.org/W6713057566","https://openalex.org/W6736057607","https://openalex.org/W6743661861","https://openalex.org/W6748304690","https://openalex.org/W6755682341","https://openalex.org/W6758448228","https://openalex.org/W6767064347","https://openalex.org/W6768532476","https://openalex.org/W6774676074","https://openalex.org/W6784919131","https://openalex.org/W6785440099","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W3183901164","https://openalex.org/W4206357785","https://openalex.org/W4281381188","https://openalex.org/W2951211570","https://openalex.org/W3192840557","https://openalex.org/W3176438653","https://openalex.org/W3167935049"],"abstract_inverted_index":{"Deep":[0],"Neural":[1,5],"Networks,":[2],"particularly":[3],"Convolutional":[4],"Networks":[6],"(ConvNets),":[7],"have":[8],"achieved":[9],"incredible":[10],"success":[11],"in":[12,47,137],"many":[13],"vision":[14],"tasks,":[15,119],"but":[16],"they":[17],"usually":[18],"require":[19,107],"millions":[20],"of":[21,35,49,69,90,95,98,112],"parameters":[22,89],"for":[23,37,72,140],"good":[24],"accuracy":[25,156],"performance.":[26],"With":[27,117],"increasing":[28],"applications":[29],"that":[30,65,86,106,149],"use":[31],"ConvNets,":[32],"updating":[33],"hundreds":[34],"networks":[36],"multiple":[38,118],"tasks":[39],"on":[40,129,162],"an":[41,109],"embedded":[42],"device":[43],"can":[44],"be":[45],"costly":[46],"terms":[48],"memory,":[50],"bandwidth,":[51],"and":[52,62,127,143],"energy.":[53],"Approaches":[54],"to":[55,153,158],"reduce":[56],"this":[57,135],"cost":[58],"include":[59],"model":[60],"compression":[61],"parameter-efficient":[63,81,160],"models":[64],"adapt":[66],"a":[67,79,91,96],"subset":[68,97],"network":[70,93,115],"layers":[71],"each":[73],"new":[74],"task.":[75],"This":[76],"work":[77],"proposes":[78],"novel":[80],"kernel":[82,104],"modulation":[83],"(KM)":[84],"method":[85,136],"adapts":[87],"all":[88],"base":[92,114],"instead":[94],"layers.":[99],"KM":[100,123,150],"uses":[101],"lightweight":[102],"task-specialized":[103,122],"modulators":[105],"only":[108,120],"additional":[110],"1.4%":[111],"the":[113,121,130,163],"parameters.":[116],"weights":[124],"are":[125],"communicated":[126],"stored":[128],"end-user":[131],"device.":[132],"We":[133],"applied":[134],"training":[138],"ConvNets":[139],"Transfer":[141,164],"Learning":[142,165],"Meta-Learning":[144],"scenarios.":[145],"Our":[146],"results":[147],"show":[148],"delivers":[151],"up":[152],"9%":[154],"higher":[155],"compared":[157],"other":[159],"methods":[161],"benchmark.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}