{"id":"https://openalex.org/W7160261332","doi":"https://doi.org/10.1109/lsp.2026.3691024","title":"A Frame-Theoretic Approach to Robust Filter Pruning in Convolutional Neural Networks","display_name":"A Frame-Theoretic Approach to Robust Filter Pruning in Convolutional Neural Networks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160261332","doi":"https://doi.org/10.1109/lsp.2026.3691024"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2026.3691024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3691024","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/A5069658303","display_name":"Pradyumna Pradhan","orcid":"https://orcid.org/0009-0008-6807-5195"},"institutions":[{"id":"https://openalex.org/I84279003","display_name":"Indian Institute of Petroleum","ror":"https://ror.org/04gavx394","country_code":"IN","type":"facility","lineage":["https://openalex.org/I2799351866","https://openalex.org/I4210134808","https://openalex.org/I66760702","https://openalex.org/I84279003"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pradyumna Pradhan","raw_affiliation_strings":["Department of Humanities and Sciences (Mathematics), Indian Institute of Petroleum and Energy, Visakhapatnam, India"],"raw_orcid":"https://orcid.org/0009-0008-6807-5195","affiliations":[{"raw_affiliation_string":"Department of Humanities and Sciences (Mathematics), Indian Institute of Petroleum and Energy, Visakhapatnam, India","institution_ids":["https://openalex.org/I84279003"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042992454","display_name":"Pradip Sasmal","orcid":"https://orcid.org/0000-0003-0111-2509"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pradip Sasmal","raw_affiliation_strings":["Department of Mathematics, Indian Institute of Technology Jodhpur, Jheepasani, India"],"raw_orcid":"https://orcid.org/0000-0003-0111-2509","affiliations":[{"raw_affiliation_string":"Department of Mathematics, Indian Institute of Technology Jodhpur, Jheepasani, India","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092865534","display_name":"Ramunaidu Randhi","orcid":"https://orcid.org/0009-0004-4044-9782"},"institutions":[{"id":"https://openalex.org/I84279003","display_name":"Indian Institute of Petroleum","ror":"https://ror.org/04gavx394","country_code":"IN","type":"facility","lineage":["https://openalex.org/I2799351866","https://openalex.org/I4210134808","https://openalex.org/I66760702","https://openalex.org/I84279003"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ramunaidu Randhi","raw_affiliation_strings":["Department of Humanities and Sciences (Mathematics), Indian Institute of Petroleum and Energy, Visakhapatnam, India"],"raw_orcid":"https://orcid.org/0009-0004-4044-9782","affiliations":[{"raw_affiliation_string":"Department of Humanities and Sciences (Mathematics), Indian Institute of Petroleum and Energy, Visakhapatnam, India","institution_ids":["https://openalex.org/I84279003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68718649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1991","last_page":"1995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.08380000293254852,"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":0.08380000293254852,"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/T10320","display_name":"Neural Networks and Applications","score":0.06599999964237213,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0494999997317791,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.600600004196167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5249000191688538},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.47380000352859497},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.44449999928474426},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3790999948978424},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3483000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7170000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6309000253677368},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.600600004196167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39239999651908875},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C2988922011","wikidata":"https://www.wikidata.org/wiki/Q5449244","display_name":"Filtering theory","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C50151734","wikidata":"https://www.wikidata.org/wiki/Q1759577","display_name":"Matched filter","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.2632000148296356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2026.3691024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3691024","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":[{"id":"https://openalex.org/F4320334771","display_name":"Science and Engineering Research Board","ror":"https://ror.org/03ffdsr55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Filter":[0],"pruning":[1,73,116,146],"method":[2,133],"is":[3,50],"an":[4,85],"effective":[5],"approach":[6],"to":[7,47,67,142],"eliminate":[8],"redundant":[9,77],"filters":[10,78],"in":[11,32,52],"convolutional":[12],"neural":[13],"networks.":[14],"Most":[15],"of":[16,97,151,159],"the":[17,81,95,105,121,131,152,160],"existing":[18,143],"techniques":[19],"rely":[20],"on":[21,120],"threshold":[22,110],"parameters":[23,153],"for":[24],"filter":[25,72],"selection":[26],"and":[27,54,93,99,112,127,138,149,154,157],"employ":[28],"multi-shot":[29],"pruning,":[30],"resulting":[31],"increased":[33],"computational":[34],"overhead.":[35],"In":[36],"addition,":[37],"many":[38],"methods":[39],"primarily":[40],"optimize":[41],"test":[42],"accuracy":[43,140],"while":[44,145],"overlooking":[45],"robustness":[46,92,135],"noise,":[48,68],"which":[49],"critical":[51],"practical":[53],"safety-critical":[55],"applications.":[56],"Since":[57],"Incoherent":[58],"Unit":[59],"Norm":[60],"Tight":[61],"Frames":[62],"(IUNTFs)":[63],"are":[64],"inherently":[65],"robust":[66],"we":[69],"propose":[70],"a":[71,114],"technique":[74],"that":[75,80,130],"removes":[76],"such":[79],"retained":[82],"set":[83],"approximates":[84],"IUNTF":[86],"structure.":[87],"This":[88],"structure":[89],"enhances":[90],"noise":[91,137],"promotes":[94],"extraction":[96],"diverse":[98],"complementary":[100],"features.":[101],"Unlike":[102],"conventional":[103],"approaches,":[104],"proposed":[106,132],"framework":[107],"requires":[108],"no":[109],"tuning":[111],"adopts":[113],"one-shot":[115],"strategy.":[117],"Experimental":[118],"results":[119],"CIFAR-10":[122],"dataset":[123],"using":[124],"VGG-16,":[125],"ResNet-56,":[126],"GoogLeNet":[128],"demonstrate":[129],"achieves":[134],"under":[136],"improved":[139],"compared":[141],"approaches":[144],"85.12%,":[147],"57%,":[148,156],"59%":[150],"69.66%,":[155],"58%":[158],"FLOPs,":[161],"respectively.":[162]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}