{"id":"https://openalex.org/W2977665223","doi":"https://doi.org/10.1109/ijcnn.2019.8852442","title":"Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining","display_name":"Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2977665223","doi":"https://doi.org/10.1109/ijcnn.2019.8852442","mag":"2977665223"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","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/A5086509276","display_name":"Yasutoshi Ida","orcid":"https://orcid.org/0000-0003-4279-9503"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yasutoshi Ida","raw_affiliation_strings":["NTT, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101917967","display_name":"Yasuhiro Fujiwara","orcid":"https://orcid.org/0000-0001-9578-1118"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuhiro Fujiwara","raw_affiliation_strings":["NTT, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086509276"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57317444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9993000030517578,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/implosion","display_name":"Implosion","score":0.8376556634902954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7642489075660706},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.7036542892456055},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.619572639465332},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6089863181114197},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5461039543151855},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4598707854747772},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.43055811524391174},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.4153420329093933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4103028178215027},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34286972880363464},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3370456099510193},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28523606061935425},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.15064570307731628}],"concepts":[{"id":"https://openalex.org/C196046385","wikidata":"https://www.wikidata.org/wiki/Q523919","display_name":"Implosion","level":3,"score":0.8376556634902954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642489075660706},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.7036542892456055},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.619572639465332},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6089863181114197},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5461039543151855},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4598707854747772},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43055811524391174},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.4153420329093933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4103028178215027},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34286972880363464},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3370456099510193},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28523606061935425},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.15064570307731628},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C82706917","wikidata":"https://www.wikidata.org/wiki/Q10251","display_name":"Plasma","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1608733719","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1720114023","https://openalex.org/W1821462560","https://openalex.org/W1836465849","https://openalex.org/W1994616650","https://openalex.org/W2034276439","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2134797427","https://openalex.org/W2149933564","https://openalex.org/W2151643194","https://openalex.org/W2161388792","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2233116163","https://openalex.org/W2292929658","https://openalex.org/W2302255633","https://openalex.org/W2408279554","https://openalex.org/W2541674938","https://openalex.org/W2561368111","https://openalex.org/W2561907692","https://openalex.org/W2579551885","https://openalex.org/W2579923771","https://openalex.org/W2592329255","https://openalex.org/W2734271713","https://openalex.org/W2740560623","https://openalex.org/W2769856846","https://openalex.org/W2774627531","https://openalex.org/W2795409696","https://openalex.org/W2949242443","https://openalex.org/W2951603627","https://openalex.org/W2962835968","https://openalex.org/W2962857907","https://openalex.org/W2962944050","https://openalex.org/W2963000224","https://openalex.org/W2963382930","https://openalex.org/W2963410064","https://openalex.org/W2963674932","https://openalex.org/W2964137095","https://openalex.org/W2964236304","https://openalex.org/W3102242707","https://openalex.org/W3118608800","https://openalex.org/W4297813707","https://openalex.org/W4299518610","https://openalex.org/W6622239757","https://openalex.org/W6636441265","https://openalex.org/W6637373629","https://openalex.org/W6637414576","https://openalex.org/W6638523607","https://openalex.org/W6638667902","https://openalex.org/W6645550903","https://openalex.org/W6679909955","https://openalex.org/W6682132143","https://openalex.org/W6683595889","https://openalex.org/W6696861079","https://openalex.org/W6698183232","https://openalex.org/W6714181750","https://openalex.org/W6725543821","https://openalex.org/W6729059855","https://openalex.org/W6730419752","https://openalex.org/W6730741096","https://openalex.org/W6732517885","https://openalex.org/W6741047420","https://openalex.org/W6746114988","https://openalex.org/W6746514494","https://openalex.org/W6747037017"],"related_works":["https://openalex.org/W2948816271","https://openalex.org/W2956199654","https://openalex.org/W2790749657","https://openalex.org/W3139123974","https://openalex.org/W2990735210","https://openalex.org/W2899067310","https://openalex.org/W2948294146","https://openalex.org/W3207443393","https://openalex.org/W3212544770","https://openalex.org/W2949270339","https://openalex.org/W2808568129","https://openalex.org/W3115260384","https://openalex.org/W3122378989","https://openalex.org/W3214535132","https://openalex.org/W2990832304","https://openalex.org/W3013134448","https://openalex.org/W3193259844","https://openalex.org/W2998981231","https://openalex.org/W3213012718","https://openalex.org/W3109051940"],"abstract_inverted_index":{"Residual":[0,57],"Networks":[1,58],"with":[2,131],"convolutional":[3],"layers":[4,39,55,82,120,152],"are":[5],"widely":[6],"used":[7],"in":[8,31,103,158],"the":[9,35,73,85,91,97,149],"field":[10],"of":[11,37,75,151],"machine":[12],"learning.":[13],"Since":[14],"they":[15,26],"effectively":[16],"extract":[17],"features":[18],"from":[19,56,133],"input":[20],"data":[21],"by":[22,153],"stacking":[23,36],"multiple":[24,54],"layers,":[25],"can":[27,79,118],"achieve":[28,125],"high":[29],"accuracy":[30,104,122,127],"many":[32,38],"applications.":[33],"However,":[34],"raises":[40],"their":[41],"computation":[42],"costs.":[43],"To":[44],"address":[45],"this":[46],"problem,":[47],"we":[48,78,95],"propose":[49],"Network":[50,139],"Implosion,":[51],"it":[52],"erases":[53],"without":[59,121,155],"degrading":[60],"accuracy.":[61,159],"Our":[62,135],"key":[63],"idea":[64],"is":[65,129],"to":[66,84,99],"introduce":[67],"a":[68,76],"priority":[69,86],"term":[70],"that":[71,112,138],"identifies":[72],"importance":[74],"layer;":[77],"select":[80],"unimportant":[81],"according":[83],"and":[87,115,124,146],"erase":[88,119],"them":[89],"after":[90,105],"training.":[92],"In":[93],"addition,":[94],"retrain":[96],"networks":[98],"avoid":[100],"critical":[101],"drops":[102],"layer":[106],"erasure.":[107],"A":[108],"theoretical":[109],"assessment":[110],"reveals":[111],"our":[113],"\"erasure":[114],"retraining\"":[116],"scheme":[117],"drop,":[123],"higher":[126],"than":[128],"possible":[130],"training":[132],"scratch.":[134],"experiments":[136],"show":[137],"Implosion":[140],"can,":[141],"for":[142],"classification":[143],"on":[144],"Cifar-10/100":[145],"ImageNet,":[147],"reduce":[148],"number":[150],"24.00%~42.86%":[154],"any":[156],"drop":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}