{"id":"https://openalex.org/W4304142412","doi":"https://doi.org/10.1145/3503161.3547983","title":"Learning an Inference-accelerated Network from a Pre-trained Model with Frequency-enhanced Feature Distillation","display_name":"Learning an Inference-accelerated Network from a Pre-trained Model with Frequency-enhanced Feature Distillation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304142412","doi":"https://doi.org/10.1145/3503161.3547983"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547983","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547983","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5017662559","display_name":"Xuesong Niu","orcid":"https://orcid.org/0000-0001-7737-4287"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuesong Niu","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042907388","display_name":"Jili Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jili Gu","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072999655","display_name":"Guoxin Zhang","orcid":"https://orcid.org/0000-0002-9228-6063"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoxin Zhang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928510","display_name":"Pengfei Wan","orcid":"https://orcid.org/0000-0001-7225-565X"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Wan","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741750","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0002-9796-488X"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyuan Wang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017662559"],"corresponding_institution_ids":["https://openalex.org/I4401726859"],"apc_list":null,"apc_paid":null,"fwci":0.0599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.27940967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1847","last_page":"1856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9991000294685364,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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/inference","display_name":"Inference","score":0.743137776851654},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7258327603340149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7217764854431152},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6467018723487854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6164757013320923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5560956597328186},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5028972029685974},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4859544038772583},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4830080270767212},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.454944372177124},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45081597566604614},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.442116379737854},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4294169843196869},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4038540720939636},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35247448086738586},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15796303749084473},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1035260558128357}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.743137776851654},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7258327603340149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7217764854431152},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6467018723487854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6164757013320923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5560956597328186},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5028972029685974},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4859544038772583},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4830080270767212},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.454944372177124},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45081597566604614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.442116379737854},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4294169843196869},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4038540720939636},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35247448086738586},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15796303749084473},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1035260558128357},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547983","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547983","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","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":26,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2614256707","https://openalex.org/W2620998106","https://openalex.org/W2807961551","https://openalex.org/W2886851211","https://openalex.org/W2912083425","https://openalex.org/W2913059114","https://openalex.org/W2924515500","https://openalex.org/W2928165649","https://openalex.org/W2963125010","https://openalex.org/W2963140444","https://openalex.org/W2963163009","https://openalex.org/W2963363373","https://openalex.org/W2964233199","https://openalex.org/W2969985801","https://openalex.org/W2982083293","https://openalex.org/W2982157312","https://openalex.org/W2988396473","https://openalex.org/W2990503944","https://openalex.org/W2998715470","https://openalex.org/W3034797615","https://openalex.org/W3035424951","https://openalex.org/W3103753223","https://openalex.org/W3177196641","https://openalex.org/W4312443924"],"related_works":["https://openalex.org/W1495042958","https://openalex.org/W2494338568","https://openalex.org/W2122678784","https://openalex.org/W2282510344","https://openalex.org/W139987158","https://openalex.org/W2183994405","https://openalex.org/W1875646599","https://openalex.org/W1976807322","https://openalex.org/W2349023125","https://openalex.org/W4309346246"],"abstract_inverted_index":{"Convolution":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"have":[4,267],"achieved":[5],"great":[6],"success":[7],"in":[8,93],"various":[9,257],"computer":[10],"vision":[11],"tasks,":[12],"but":[13,45],"they":[14],"are":[15,24,160,216,246],"still":[16],"suffering":[17],"from":[18,27,80,222],"the":[19,28,32,73,88,100,111,132,137,142,148,153,163,172,176,180,184,190,203,208,220,223,227,231,236,240,271],"heavy":[20],"computation":[21,113,291],"costs,":[22],"which":[23,70,201],"mainly":[25],"resulted":[26],"substantial":[29],"redundancy":[30],"of":[31,91,115,175,193],"feature":[33,48,78,104,119,143,158,177,191,199,242,274],"maps.":[34,144],"In":[35,84],"order":[36,85],"to":[37,51,86,98,106,109,130,135,183,218,226],"reduce":[38,110],"these":[39],"redundancy,":[40],"we":[41,96,187],"proposed":[42,272],"a":[43,57,67,124,197],"simple":[44],"effective":[46],"frequency-enhanced":[47,118,198,214,273],"distillation":[49,120,275],"strategy":[50,122],"train":[52],"an":[53,282],"inference-accelerated":[54,133,154,283],"network":[55,134,151,155,165,168,225,258,284],"with":[56,123,156,270,285],"pre-trained":[58,125,150],"model.":[59],"Traditionally,":[60],"one":[61],"CNN":[62],"can":[63,71],"be":[64,146],"regarded":[65,161],"as":[66,162],"hierarchical":[68],"structure,":[69],"generate":[72],"low-level,":[74],"middle-level":[75,103],"and":[76,102,152,166,210,243,265,288],"high-level":[77],"maps":[79,105,159,178,192],"different":[81,194],"convolution":[82],"layers.":[83],"accelerate":[87],"inference":[89],"time":[90],"CNNs,":[92],"this":[94],"paper,":[95],"propose":[97],"resize":[99],"low-level":[101],"smaller":[107],"scales":[108],"spatial":[112],"costs":[114],"CNNs.":[116],"A":[117],"training":[121,276],"model":[126],"is":[127],"then":[128,188],"used":[129,217,248],"help":[131],"maintain":[136],"core":[138],"information":[139],"after":[140],"resizing":[141],"To":[145],"specific,":[147],"original":[149],"resized":[157],"teacher":[164,209,224],"student":[167,211,228],"respectively.":[169],"Considering":[170],"that":[171,269],"low-frequency":[173,204],"domain":[174],"contribute":[179],"most":[181],"parts":[182],"final":[185,237],"classification,":[186,238],"transform":[189],"levels":[195],"into":[196],"space,":[200],"highlights":[202],"features":[205,215],"for":[206,235,249],"both":[207],"networks.":[212],"The":[213],"transfer":[219],"knowledge":[221,234],"network.":[229],"At":[230],"same":[232],"time,":[233],"i.e.,":[239],"classification":[241],"predicted":[244],"probabilities,":[245],"also":[247],"distillation.":[250],"Experiments":[251],"on":[252,256],"multiple":[253],"databases":[254],"based":[255],"structure":[259],"types,":[260],"e.g.,":[261],"ResNet,":[262],"Res2Net,":[263],"MobileNetV2,":[264],"ConvNeXt,":[266],"shown":[268],"strategy,":[277],"our":[278],"method":[279],"could":[280],"get":[281],"comparable":[286],"performance":[287],"much":[289],"less":[290],"cost.":[292]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}