{"id":"https://openalex.org/W7131405311","doi":"https://doi.org/10.1109/access.2026.3667719","title":"PoinT: Robust Fine-Tuning for Lightweight Convolutional Neural Networks","display_name":"PoinT: Robust Fine-Tuning for Lightweight Convolutional Neural Networks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131405311","doi":"https://doi.org/10.1109/access.2026.3667719"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3667719","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667719","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2026.3667719","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101806003","display_name":"Jinxiao Wang","orcid":"https://orcid.org/0000-0002-6692-229X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxiao Wang","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6692-229X","affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101277121","display_name":"Benkui Zhang","orcid":"https://orcid.org/0009-0007-0729-4995"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Benkui Zhang","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuan Liu","orcid":"https://orcid.org/0000-0002-6659-3772"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Liu","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6659-3772","affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709184","display_name":"Xinyu Zhao","orcid":"https://orcid.org/0000-0002-5128-4424"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Zhao","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":null,"display_name":"Pengcheng Wang","orcid":"https://orcid.org/0009-0004-4427-1432"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Wang","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-4427-1432","affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18262786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"32158","last_page":"32169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5954999923706055,"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":0.5954999923706055,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.10459999740123749,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.04149999842047691,"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/robustness","display_name":"Robustness (evolution)","score":0.7565000057220459},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6588000059127808},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.570900022983551},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.48260000348091125},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.47769999504089355},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44839999079704285},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44440001249313354},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.44429999589920044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518000245094299},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7565000057220459},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6588000059127808},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.570900022983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5094000101089478},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.47769999504089355},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3741999864578247},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.3260999917984009},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.30320000648498535},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3667719","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667719","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:305b4dd326a248a087bb6c189c9bc107","is_oa":true,"landing_page_url":"https://doaj.org/article/305b4dd326a248a087bb6c189c9bc107","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 14, Pp 32158-32169 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3667719","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3667719","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Targeted":[0],"fine-tuning":[1,66,78,94],"of":[2,50,100,150,216,224],"lightweight":[3,44,69,90],"convolutional":[4],"neural":[5],"networks":[6],"(CNNs)":[7],"is":[8,81,153,189],"a":[9,48,77,98,114],"core":[10],"approach":[11],"to":[12,16,18,40,158,176],"enabling":[13,156],"edge":[14,37],"devices":[15],"adapt":[17],"personalized":[19],"scenarios":[20],"with":[21,43,83,119,124],"limited":[22],"resources.":[23],"However,":[24],"most":[25],"existing":[26],"methods":[27],"suffer":[28],"from":[29,109,131,194],"both":[30],"insufficient":[31],"adaptability":[32],"and":[33,47,64,87,103,113,141,171,183],"poor":[34],"robustness":[35],"in":[36],"scenarios,":[38],"due":[39],"their":[41],"mismatch":[42],"CNN":[45],"architectures":[46,177],"lack":[49],"specific":[51],"optimization":[52],"for":[53,68],"noisy":[54],"environments.":[55],"To":[56],"this":[57,59],"end,":[58],"paper":[60],"proposes":[61],"an":[62,209],"efficient":[63],"robust":[65,191],"method":[67],"CNNs,":[70],"which":[71],"we":[72],"call":[73],"PoinT.":[74],"PoinT":[75,96,204],"introduces":[76],"branch":[79],"that":[80,186,215],"consistent":[82],"the":[84,93,104,110,139,148,168,187,201,222],"backbone\u2019s":[85],"structure":[86],"informed":[88],"by":[89,227],"CNNs.":[91],"In":[92,146],"branch,":[95],"designates":[97],"set":[99],"seed":[101,111,151],"filters,":[102],"remaining":[105],"filters":[106,112,152],"are":[107],"generated":[108],"nonlinear":[115],"transformation":[116],"function":[117],"(NTF)":[118],"configured":[120],"untrainable":[121],"parameters.":[122],"NTF":[123],"fixed":[125],"hyperparameters":[126],"prevents":[127],"model":[128,188],"parameter":[129],"updates":[130],"being":[132],"entirely":[133],"dependent":[134],"on":[135,162,167,200,206],"training":[136,193],"data,":[137],"regularizes":[138],"model,":[140],"thus":[142],"improves":[143],"its":[144],"robustness.":[145],"addition,":[147],"number":[149,223],"dynamically":[154],"controllable,":[155],"adaptation":[157],"changing":[159],"resource":[160],"availability":[161],"IoT":[163],"devices.":[164],"Experimental":[165],"results":[166],"CIFAR-10/100,":[169],"CIFAR-10-C/-100-C,":[170],"Icons-50":[172],"datasets,":[173],"when":[174],"applied":[175],"such":[178],"as":[179],"MobileNetV2,":[180],"ShuffleNetV2,":[181],"EfficientNet,":[182],"GhostNet,":[184],"demonstrate":[185],"more":[190,228],"than":[192,214,229],"scratch":[195],"or":[196],"fully":[197,217],"fine-tuning.":[198],"Specifically,":[199],"CIFAR-10-C":[202],"dataset,":[203],"based":[205],"ShuffleNetV2":[207],"achieves":[208],"accuracy":[210],"about":[211],"7.8%":[212],"higher":[213],"fine-tuned":[218],"models,":[219],"while":[220],"reducing":[221],"trainable":[225],"parameters":[226],"65%.":[230]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-26T00:00:00"}