{"id":"https://openalex.org/W4387969178","doi":"https://doi.org/10.1145/3581783.3611701","title":"Shift Pruning: Equivalent Weight Pruning for CNN via Differentiable Shift Operator","display_name":"Shift Pruning: Equivalent Weight Pruning for CNN via Differentiable Shift Operator","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969178","doi":"https://doi.org/10.1145/3581783.3611701"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611701","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st 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/A5082523958","display_name":"Tao Niu","orcid":"https://orcid.org/0000-0001-6149-2908"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Niu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063901345","display_name":"Yihang Lou","orcid":"https://orcid.org/0000-0002-8143-389X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihang Lou","raw_affiliation_strings":["Huawei Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technology, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081117495","display_name":"Yinglei Teng","orcid":"https://orcid.org/0000-0002-7170-4764"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinglei Teng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103165151","display_name":"Jianzhong He","orcid":"https://orcid.org/0000-0002-1350-7869"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhong He","raw_affiliation_strings":["Huawei Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technology, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030146102","display_name":"Yishuai Liu","orcid":"https://orcid.org/0000-0002-8739-8482"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiding Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082523958"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13457924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5445","last_page":"5454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9934999942779541,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9864000082015991,"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/flops","display_name":"FLOPS","score":0.8404961824417114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6393458247184753},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5600322484970093},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5248363614082336},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5152847766876221},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4315018355846405},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.4140196144580841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3480154275894165},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29910820722579956},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.255967915058136},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23169079422950745}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.8404961824417114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6393458247184753},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5600322484970093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5248363614082336},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5152847766876221},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4315018355846405},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.4140196144580841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3480154275894165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29910820722579956},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.255967915058136},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23169079422950745},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611701","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1134553906","display_name":null,"funder_award_id":"62171062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2798170643","https://openalex.org/W2924515500","https://openalex.org/W2928560789","https://openalex.org/W2962851801","https://openalex.org/W2963037989","https://openalex.org/W2963446712","https://openalex.org/W2963844898","https://openalex.org/W2970958999","https://openalex.org/W2984618279","https://openalex.org/W3104263540","https://openalex.org/W3106913724","https://openalex.org/W3136450870","https://openalex.org/W3173390350","https://openalex.org/W3180849877","https://openalex.org/W3196865505","https://openalex.org/W3205325461","https://openalex.org/W3207691866","https://openalex.org/W4214708455","https://openalex.org/W4285601858","https://openalex.org/W4297683907","https://openalex.org/W6600116659","https://openalex.org/W6600212071"],"related_works":["https://openalex.org/W4315697128","https://openalex.org/W4285277090","https://openalex.org/W3102845713","https://openalex.org/W2971502891","https://openalex.org/W4327738859","https://openalex.org/W3205506801","https://openalex.org/W2995343971","https://openalex.org/W2982536526","https://openalex.org/W2013435028","https://openalex.org/W2992221004"],"abstract_inverted_index":{"Weight":[0],"pruning":[1,16,27,59],"is":[2,23,62,142,149],"a":[3,56,161,167,180,189],"well-known":[4],"technique":[5],"used":[6],"for":[7,129,151,184],"network":[8],"compression.":[9],"In":[10],"contrast":[11],"to":[12,43,123,144,177,216],"filter":[13],"pruning,":[14],"weight":[15,58],"produces":[17],"higher":[18],"compression":[19,191],"ratios":[20],"as":[21],"it":[22],"more":[24,168],"fine-grained.":[25],"However,":[26],"individual":[28],"weights":[29],"results":[30],"in":[31,179,209],"broken":[32],"kernels,":[33],"which":[34,80,148],"cannot":[35],"be":[36],"directly":[37],"accelerated":[38],"on":[39,195,222,231],"general":[40,65],"platforms,":[41],"leading":[42],"hardware":[44,186],"compatibility":[45,187],"issues.":[46],"To":[47,154],"address":[48],"this":[49],"issue,":[50],"we":[51,94,159,224],"propose":[52],"Shift":[53,112],"Pruning":[54],"(SP),":[55],"novel":[57],"method":[60,205],"that":[61,85,164,202],"compatible":[63],"with":[64,133,233],"platforms.":[66],"SP":[67,176],"converts":[68],"spatial":[69,131],"convolutions":[70,76],"into":[71,102],"regular":[72],"1":[73,75],"X":[74,99],"and":[77,108,188,198,212],"shift":[78,121],"operations,":[79],"are":[81],"simply":[82],"memory":[83],"movements":[84],"do":[86],"not":[87],"require":[88],"additional":[89],"FLOPs":[90,213,230],"or":[91],"parameters.":[92],"Specifically,":[93],"decompose":[95],"the":[96,110,119,126,134,196],"original":[97],"K":[98,100],"convolution":[101],"parallel":[103],"branches":[104],"of":[105,118,228],"shift-convolution":[106],"operations":[107],"devise":[109],"Differentiable":[111],"Operator":[113],"(DSO),":[114],"an":[115],"approximation":[116],"form":[117],"actual":[120],"operation,":[122],"automatically":[124],"learn":[125],"crucial":[127],"directions":[128],"adequate":[130],"interactions":[132],"designed":[135],"shift-related":[136],"loss":[137],"function.":[138],"A":[139],"regularization":[140],"term":[141],"proposed":[143,204],"prevent":[145],"redundant":[146],"shifting,":[147],"beneficial":[150],"low-resolution":[152],"situations.":[153],"further":[155],"improve":[156],"inference":[157],"efficacy,":[158],"develop":[160],"post-training":[162],"transformation":[163],"can":[165,225],"construct":[166],"compact":[169],"model.":[170],"The":[171],"introduced":[172],"channel-wise":[173],"slimming":[174],"allows":[175],"prune":[178],"hybrid-structural":[181],"manner,":[182],"catering":[183],"both":[185,210],"high":[190],"ratio.":[192],"Extensive":[193],"experiments":[194],"CIFAR-10":[197],"ImageNet":[199],"datasets":[200],"demonstrate":[201],"our":[203],"achieves":[206],"superior":[207],"performance":[208],"accuracy":[211,237],"reduction":[214],"compared":[215],"other":[217],"state-of-the-art":[218],"techniques.":[219],"For":[220],"instance,":[221],"ImageNet,":[223],"reduce":[226],"48.8%":[227],"total":[229],"ResNet-34":[232],"only":[234],"0.22%":[235],"Top-1":[236],"drop.":[238]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}