{"id":"https://openalex.org/W4293193356","doi":"https://doi.org/10.1109/lsp.2022.3171128","title":"Layer Pruning for Obtaining Shallower ResNets","display_name":"Layer Pruning for Obtaining Shallower ResNets","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4293193356","doi":"https://doi.org/10.1109/lsp.2022.3171128"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2022.3171128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3171128","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5100365698","display_name":"Ke Zhang","orcid":"https://orcid.org/0000-0001-9696-4944"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zhang","raw_affiliation_strings":["National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"an, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073219217","display_name":"Guangzhe Liu","orcid":"https://orcid.org/0000-0001-9182-8409"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhe Liu","raw_affiliation_strings":["National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","an, China"],"raw_orcid":"https://orcid.org/0000-0001-9182-8409","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Aerospace Flight Dynamics, School of Astronautics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"an, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":2.6428,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.91366565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1172","last_page":"1176"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9980000257492065,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9966999888420105,"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/residual","display_name":"Residual","score":0.895046591758728},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7926831245422363},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7662685513496399},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7223135828971863},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6438199281692505},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.6326709985733032},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5301448106765747},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4414437413215637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27781879901885986},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11785385012626648},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07896587252616882}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.895046591758728},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7926831245422363},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7662685513496399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7223135828971863},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6438199281692505},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.6326709985733032},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5301448106765747},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4414437413215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27781879901885986},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11785385012626648},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07896587252616882},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2022.3171128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3171128","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2604998962","https://openalex.org/W2787884921","https://openalex.org/W2808168148","https://openalex.org/W2897295818","https://openalex.org/W2924515500","https://openalex.org/W2928560789","https://openalex.org/W2962851801","https://openalex.org/W2963145730","https://openalex.org/W2964233199","https://openalex.org/W2965862774","https://openalex.org/W2995046500","https://openalex.org/W2997300524","https://openalex.org/W3034513523","https://openalex.org/W3035414587","https://openalex.org/W3109037380","https://openalex.org/W3118608800","https://openalex.org/W3121699489","https://openalex.org/W3139084715","https://openalex.org/W3201292656","https://openalex.org/W6638523607","https://openalex.org/W6684191040","https://openalex.org/W6693397755","https://openalex.org/W6726275242","https://openalex.org/W6739917289","https://openalex.org/W6771832129","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W3196952692","https://openalex.org/W2984708981","https://openalex.org/W4300939921","https://openalex.org/W3008625068","https://openalex.org/W2964350391","https://openalex.org/W2274287116","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3035501883","https://openalex.org/W2967403871"],"abstract_inverted_index":{"Network":[0],"pruning":[1,53],"has":[2],"become":[3],"an":[4],"effective":[5],"scheme":[6],"to":[7,55,105,124,129,163],"cut":[8],"down":[9],"the":[10,16,33,40,63,69,72,77,84,90,96,107,114,140,151,155],"network":[11],"complexity":[12],"and":[13,60,81,94,122,144,171],"speed":[14,149],"up":[15,150],"inference.":[17,152],"Current":[18],"work":[19],"mainly":[20],"focuses":[21],"on":[22,159],"filter":[23],"pruning,":[24,39],"which":[25],"deletes":[26],"filters":[27],"in":[28,113],"a":[29,51],"structured":[30],"way.":[31],"Although":[32],"calculation":[34],"amount":[35],"is":[36,43],"reduced":[37],"after":[38],"acceleration":[41],"effect":[42],"not":[44,137],"obvious.":[45],"In":[46],"this":[47],"letter,":[48],"we":[49,75],"present":[50],"layer":[52,99],"method":[54],"obtain":[56],"shallower":[57],"ResNets":[58],"(LPSR)":[59],"significantly":[61,148],"reduce":[62],"inference":[64,173],"latency.":[65,174],"Taking":[66],"advantage":[67],"of":[68,71,98,109,142,157],"characteristics":[70],"residual":[73,79,92,115,127],"module,":[74],"disconnect":[76],"unimportant":[78,126],"mapping":[80],"reserve":[82],"only":[83,138],"identity":[85],"mapping,":[86],"thereby":[87],"equivalently":[88],"removing":[89],"corresponding":[91],"module":[93],"achieving":[95],"purpose":[97],"pruning.":[100],"We":[101],"adopt":[102],"Taylor":[103],"expansion":[104],"estimate":[106],"impact":[108],"disconnecting":[110],"BN":[111],"layers":[112],"mapping.":[116],"These":[117],"impacts":[118],"are":[119],"then":[120],"normalized":[121],"used":[123],"identify":[125],"blocks":[128],"prune.":[130],"Comprehensive":[131],"experimental":[132],"results":[133],"demonstrate":[134],"that":[135],"LPSR":[136,153],"reduces":[139],"number":[141],"parameters":[143],"calculations,":[145],"but":[146],"also":[147],"improves":[154],"accuracy":[156],"ResNet-56":[158],"CIFAR-10":[160],"from":[161],"93.21%":[162],"93.40%,":[164],"while":[165],"reducing":[166],"44.71%":[167],"parameters,":[168],"52.68%":[169],"calculations":[170],"44.89%":[172]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}