{"id":"https://openalex.org/W4403791328","doi":"https://doi.org/10.1145/3664647.3681419","title":"Adaptive Pruning of Channel Spatial Dependability in Convolutional Neural Networks","display_name":"Adaptive Pruning of Channel Spatial Dependability in Convolutional Neural Networks","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791328","doi":"https://doi.org/10.1145/3664647.3681419"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681419","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5052163069","display_name":"Weiying Xie","orcid":"https://orcid.org/0000-0001-8310-024X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiying Xie","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8310-024X","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mei Yuan","orcid":"https://orcid.org/0009-0003-9085-5191"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Yuan","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0003-9085-5191","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109042141","display_name":"Jitao Ma","orcid":"https://orcid.org/0009-0009-7782-8184"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jitao Ma","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0009-7782-8184","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067798266","display_name":"Yunsong Li","orcid":"https://orcid.org/0000-0002-0234-6270"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunsong Li","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-0234-6270","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":1.4224,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84405796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6073","last_page":"6082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9984999895095825,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9984999895095825,"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":0.9979000091552734,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dependability","display_name":"Dependability","score":0.886581540107727},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7807396650314331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7593505382537842},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6995972394943237},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.511693000793457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42874252796173096},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23317477107048035},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.07010561227798462}],"concepts":[{"id":"https://openalex.org/C77019957","wikidata":"https://www.wikidata.org/wiki/Q2689057","display_name":"Dependability","level":2,"score":0.886581540107727},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7807396650314331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7593505382537842},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6995972394943237},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.511693000793457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42874252796173096},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23317477107048035},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.07010561227798462},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681419","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2117539524","https://openalex.org/W2604998962","https://openalex.org/W2924515500","https://openalex.org/W2928560789","https://openalex.org/W2962858109","https://openalex.org/W2963382930","https://openalex.org/W2965862774","https://openalex.org/W2970958999","https://openalex.org/W3010021382","https://openalex.org/W3014249243","https://openalex.org/W3014641619","https://openalex.org/W3028304412","https://openalex.org/W3034513523","https://openalex.org/W3034522582","https://openalex.org/W3035160371","https://openalex.org/W3046669193","https://openalex.org/W3090140268","https://openalex.org/W3091174280","https://openalex.org/W3095508601","https://openalex.org/W3104151879","https://openalex.org/W3135688577","https://openalex.org/W3154360923","https://openalex.org/W3168076195","https://openalex.org/W3185855491","https://openalex.org/W3187760974","https://openalex.org/W3193164413","https://openalex.org/W3193347070","https://openalex.org/W3205652345","https://openalex.org/W3210655452","https://openalex.org/W3211730381","https://openalex.org/W4213016094","https://openalex.org/W4213060227","https://openalex.org/W4213084750","https://openalex.org/W4224267386","https://openalex.org/W4226146794","https://openalex.org/W4226426325","https://openalex.org/W4285603559","https://openalex.org/W4287828539","https://openalex.org/W4289313596","https://openalex.org/W4310895557","https://openalex.org/W4385801596","https://openalex.org/W4386076113","https://openalex.org/W4386083031","https://openalex.org/W4390872453","https://openalex.org/W4390873324","https://openalex.org/W4390873603","https://openalex.org/W4390873955","https://openalex.org/W6774302960"],"related_works":["https://openalex.org/W4252527915","https://openalex.org/W2409287660","https://openalex.org/W2233357156","https://openalex.org/W1976489385","https://openalex.org/W4256317220","https://openalex.org/W1506225852","https://openalex.org/W2141414364","https://openalex.org/W2376514150","https://openalex.org/W1523265213","https://openalex.org/W2363668972"],"abstract_inverted_index":{"Deep":[0],"Convolutional":[1],"Neural":[2],"Networks":[3],"(CNNs)":[4],"have":[5],"demonstrated":[6],"excellent":[7],"performance":[8,161],"in":[9,141,163],"various":[10],"multimedia":[11,35],"application":[12,36],"scenarios.":[13],"However,":[14,42],"complex":[15],"models":[16],"often":[17],"require":[18],"significant":[19,176],"computational":[20],"resources":[21],"and":[22,84,117,137,169,184],"energy":[23],"costs.":[24],"Therefore,":[25],"CNN":[26,44,67],"compression":[27],"is":[28],"crucial":[29],"for":[30],"addressing":[31],"deployment":[32],"challenges":[33],"of":[34,55,73,98,119,139,156,181,201],"on":[37,50,89,124,160,193],"resource":[38],"constrained":[39],"edge":[40],"devices.":[41],"existing":[43],"channel":[45,81,100],"pruning":[46,68,154,192],"strategies":[47,69],"primarily":[48],"focus":[49],"the":[51,56,71,78,96,102,114,135,153,194],"\"weights\"":[52],"or":[53,205],"\"activations\"":[54],"model,":[57],"overlooking":[58],"its":[59],"\"interpretability\"":[60],"information.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,106,126,150,188],"explore":[66],"from":[70],"perspective":[72],"model":[74,77,147,196],"interpretability.":[75],"We":[76],"correspondence":[79],"between":[80],"feature":[82],"maps":[83],"interpretable":[85],"visual":[86],"perception":[87],"based":[88,159],"class":[90,120],"saliency":[91,121],"maps,":[92],"aiming":[93],"to":[94,101,112,145,165],"assess":[95],"contribution":[97,138],"each":[99,157],"desired":[103],"output.":[104],"Additionally,":[105],"utilize":[107],"Discrete":[108],"Wavelet":[109],"Transform":[110],"(DWT)":[111],"capture":[113],"global":[115],"features":[116],"structure":[118],"maps.":[122],"Based":[123],"this,":[125],"propose":[127],"a":[128,142,179,190],"Channel":[129],"Spatial":[130],"Dependability":[131],"(CSD)":[132],"metric,":[133],"evaluating":[134],"importance":[136],"channels":[140],"bidirectional":[143],"manner":[144],"guide":[146],"pruning.":[148,172],"And":[149],"dynamically":[151],"adjust":[152],"rate":[155],"layer":[158],"changes,":[162],"order":[164],"achieve":[166],"more":[167],"accurate":[168],"efficient":[170],"adaptive":[171],"Our":[173],"method":[174],"achieves":[175],"results":[177],"across":[178],"range":[180],"different":[182],"networks":[183],"datasets.":[185],"For":[186],"instance,":[187],"achieved":[189],"51.3%":[191],"ResNet-56":[195],"while":[197],"maintaining":[198],"an":[199],"accuracy":[200],"94.16%,":[202],"outperforming":[203],"feature-map":[204],"other":[206],"State-of-the-Art":[207],"(SOTA).":[208]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}