{"id":"https://openalex.org/W4399875132","doi":"https://doi.org/10.1109/access.2024.3416997","title":"Channel Pruning of Transfer Learning Models Using Novel Techniques","display_name":"Channel Pruning of Transfer Learning Models Using Novel Techniques","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399875132","doi":"https://doi.org/10.1109/access.2024.3416997"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3416997","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3416997","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3416997","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078852529","display_name":"Pragnesh Thaker","orcid":"https://orcid.org/0000-0001-7702-8130"},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pragnesh Thaker","raw_affiliation_strings":["National Institute of Technology Karnataka, Surathkal, Srinivasnagar, India"],"raw_orcid":"https://orcid.org/0000-0001-7702-8130","affiliations":[{"raw_affiliation_string":"National Institute of Technology Karnataka, Surathkal, Srinivasnagar, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032581304","display_name":"Biju R. Mohan","orcid":"https://orcid.org/0000-0002-3928-8924"},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Biju R. Mohan","raw_affiliation_strings":["National Institute of Technology Karnataka, Surathkal, Srinivasnagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Karnataka, Surathkal, Srinivasnagar, India","institution_ids":["https://openalex.org/I11880225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I11880225"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.8957,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77951858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"12","issue":null,"first_page":"94914","last_page":"94925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9962000250816345,"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/T12676","display_name":"Machine Learning and ELM","score":0.9962000250816345,"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":0.9937000274658203,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.991100013256073,"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/computer-science","display_name":"Computer science","score":0.6961506009101868},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6546705365180969},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6425271034240723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4846682846546173},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43862199783325195},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3835635185241699},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11792182922363281}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6961506009101868},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6546705365180969},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6425271034240723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4846682846546173},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43862199783325195},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3835635185241699},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11792182922363281},{"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":2,"locations":[{"id":"doi:10.1109/access.2024.3416997","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3416997","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e45c645f1caf4c91bc29eae38e469b3a","is_oa":true,"landing_page_url":"https://doaj.org/article/e45c645f1caf4c91bc29eae38e469b3a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 94914-94925 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3416997","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3416997","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325375","display_name":"National Institute of Technology Karnataka, Surathkal","ror":"https://ror.org/01hz4v948"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1904365287","https://openalex.org/W1996901117","https://openalex.org/W2097117768","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2276892413","https://openalex.org/W2807961551","https://openalex.org/W2808168148","https://openalex.org/W2887280559","https://openalex.org/W2924515500","https://openalex.org/W2928560789","https://openalex.org/W2949763090","https://openalex.org/W2962965870","https://openalex.org/W2963140066","https://openalex.org/W2963223345","https://openalex.org/W2963363373","https://openalex.org/W2964054038","https://openalex.org/W2966256598","https://openalex.org/W2974735009","https://openalex.org/W2976540144","https://openalex.org/W2984618279","https://openalex.org/W3080599598","https://openalex.org/W3103105237","https://openalex.org/W3160499679","https://openalex.org/W3176231905","https://openalex.org/W3180037928","https://openalex.org/W3181161645","https://openalex.org/W4229452442","https://openalex.org/W4283812641","https://openalex.org/W4285816460","https://openalex.org/W4308475351","https://openalex.org/W4312796067","https://openalex.org/W4312950795","https://openalex.org/W4324057834","https://openalex.org/W4372232585","https://openalex.org/W4394566113","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638444622","https://openalex.org/W6640036494","https://openalex.org/W6684191040","https://openalex.org/W6726275242","https://openalex.org/W6730382033","https://openalex.org/W6739917289","https://openalex.org/W6754938779","https://openalex.org/W6802897275","https://openalex.org/W6802984017"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"This":[0,128],"research":[1,77],"paper":[2],"delves":[3],"into":[4],"the":[5,18,49,85,90,95,112,117,125,131,164,201,205,218,240,277,280],"challenges":[6],"associated":[7],"with":[8,264,276],"deep":[9],"learning":[10],"models,":[11],"specifically":[12],"focusing":[13],"on":[14,32,72],"transfer":[15],"learning.":[16],"Despite":[17],"effectiveness":[19],"of":[20,116,120,203,228],"widely":[21],"used":[22],"models":[23],"such":[24],"as":[25,53],"VGGNet,":[26],"ResNet,":[27],"and":[28,41,44,79,94,137,145,157,176,194,215,243,254,271,283],"GoogLeNet,":[29],"their":[30],"deployment":[31],"resource-constrained":[33],"devices":[34],"is":[35,130,182,237],"impeded":[36],"by":[37,110],"high":[38],"memory":[39],"bandwidth":[40],"computational":[42,67],"costs,":[43,68],"to":[45,66,123],"overcome":[46],"these":[47],"limitations,":[48],"study":[50],"proposes":[51],"pruning":[52,83,88,104,167,180,235,248,285],"a":[54,107,151,158,171,187,195,209,225,255,265],"viable":[55],"solution.":[56],"Numerous":[57],"parameters,":[58],"particularly":[59],"in":[60,155,161,174,186,190,198,212,258,268,289],"fully":[61],"connected":[62],"layers,":[63],"contribute":[64],"minimally":[65],"so":[69],"we":[70],"focus":[71],"convolution":[73],"layers\u2019":[74],"pruning.":[75],"The":[76,101,178,246],"explores":[78],"evaluates":[80],"three":[81,113],"innovative":[82],"methods:":[84],"Max3":[86,102,165,241,281],"Saliency":[87,103,166,242,282],"method,":[89,168],"K-Means":[91,179,206,244,284],"clustering":[92],"algorithm,":[93],"Singular":[96,219],"Value":[97,220],"Decomposition":[98,221],"(SVD)":[99,222],"approach.":[100],"method":[105,129,249],"introduces":[106],"slight":[108],"variation":[109],"using":[111],"maximum":[114],"values":[115,229],"kernel":[118],"instead":[119],"all":[121],"nine":[122],"compute":[124],"saliency":[126],"score.":[127],"most":[132],"effective,":[133],"substantially":[134],"reducing":[135],"parameter":[136,252],"Floating":[138],"Point":[139],"Operations":[140],"(FLOPs)":[141],"for":[142,192,230,261,273],"both":[143,213,269],"VGG16":[144,149,193],"ResNet56":[146,169],"models.":[147],"Notably,":[148],"demonstrates":[150],"remarkable":[152],"46.19%":[153],"reduction":[154,160,173,189,197,211,253,257,267,291],"parameters":[156,175,191,214,272],"61.91%":[159],"FLOPs.":[162,177,199,216],"Using":[163],"shows":[170],"35.15%":[172],"algorithm":[181,207],"also":[183],"successful,":[184],"resulting":[185],"40.00%":[188],"49.20%":[196],"In":[200],"case":[202],"ResNet56,":[204],"achieved":[208,260],"31.01%":[210],"While":[217],"approach":[223],"provides":[224],"new":[226],"set":[227],"condensed":[231],"channels,":[232],"its":[233],"overall":[234],"ratio":[236],"smaller":[238],"than":[239],"methods.":[245],"SVD":[247],"prunes":[250],"20.07%":[251],"24.64%":[256],"FLOPs":[259,270],"VGG16,":[262],"along":[263],"16.94%":[266],"ResNet56.":[274],"Compared":[275],"state-of-the-art":[278],"methods,":[279],"methods":[286],"performed":[287],"better":[288],"Flops":[290],"metrics.":[292]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}