{"id":"https://openalex.org/W4410583432","doi":"https://doi.org/10.1109/access.2025.3572415","title":"Enhancing Early Exit Performance With Uncertainty-Aware Training in Convolutional Neural Networks for Image Classification","display_name":"Enhancing Early Exit Performance With Uncertainty-Aware Training in Convolutional Neural Networks for Image Classification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410583432","doi":"https://doi.org/10.1109/access.2025.3572415"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3572415","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3572415","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.2025.3572415","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092000916","display_name":"Thanu Kurian","orcid":"https://orcid.org/0009-0006-1559-2645"},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Thanu Kurian","raw_affiliation_strings":["Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Bengaluru, India"],"raw_orcid":"https://orcid.org/0009-0006-1559-2645","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Bengaluru, India","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"last","author":{"id":null,"display_name":"Somasundaram Thangam","orcid":"https://orcid.org/0000-0001-9284-7724"},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Somasundaram Thangam","raw_affiliation_strings":["Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0001-9284-7724","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Bengaluru, India","institution_ids":["https://openalex.org/I81556334"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I81556334"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.792,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90555519,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"91671","last_page":"91681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8138999938964844,"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/T10320","display_name":"Neural Networks and Applications","score":0.8138999938964844,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.7473999857902527,"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":0.8231275677680969},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7440093159675598},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.6281441450119019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6157209873199463},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5811735391616821},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5186452269554138},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46297189593315125},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41775691509246826},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4155727028846741},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4143731892108917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8231275677680969},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7440093159675598},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.6281441450119019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6157209873199463},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5811735391616821},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5186452269554138},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46297189593315125},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41775691509246826},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4155727028846741},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4143731892108917},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3572415","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3572415","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:37a6e77b7ab84a3fba65e3be7cdb3c7c","is_oa":true,"landing_page_url":"https://doaj.org/article/37a6e77b7ab84a3fba65e3be7cdb3c7c","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 13, Pp 91671-91681 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3572415","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3572415","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":31,"referenced_works":["https://openalex.org/W2754726293","https://openalex.org/W2962677625","https://openalex.org/W2962814013","https://openalex.org/W2962991582","https://openalex.org/W2965583023","https://openalex.org/W3006466613","https://openalex.org/W3017918656","https://openalex.org/W3019321633","https://openalex.org/W3046605870","https://openalex.org/W3102100346","https://openalex.org/W3126684630","https://openalex.org/W3128348732","https://openalex.org/W3190730109","https://openalex.org/W3206423279","https://openalex.org/W3210027319","https://openalex.org/W4206392460","https://openalex.org/W4211103858","https://openalex.org/W4282043616","https://openalex.org/W4284879859","https://openalex.org/W4289515874","https://openalex.org/W4296982580","https://openalex.org/W4312090285","https://openalex.org/W4313006223","https://openalex.org/W4327970403","https://openalex.org/W4360993143","https://openalex.org/W4401875432","https://openalex.org/W6617145748","https://openalex.org/W6745447533","https://openalex.org/W6762100871","https://openalex.org/W6802266821","https://openalex.org/W6802497872"],"related_works":["https://openalex.org/W4394050964","https://openalex.org/W2911497689","https://openalex.org/W2952813363","https://openalex.org/W2963346891","https://openalex.org/W4360783045","https://openalex.org/W2770149305","https://openalex.org/W3167930666","https://openalex.org/W2551249631","https://openalex.org/W3014952856","https://openalex.org/W3010730661"],"abstract_inverted_index":{"Deep":[0,78,193],"Neural":[1,79],"Networks":[2,80],"have":[3,44],"become":[4],"more":[5,7,18],"and":[6,42,58,92,109,116,163,170],"complex":[8],"over":[9],"the":[10,38,51,56,59,129,138,145,181],"past":[11],"years":[12],"delivering":[13],"efficient":[14],"results":[15,97,155],"but":[16],"demanding":[17],"requirements":[19],"for":[20,71,152],"resources.":[21],"The":[22],"traditional":[23],"cloud-based":[24],"DNN":[25,67],"inference":[26],"produces":[27],"poor":[28],"real-time":[29],"performance":[30,122,186],"due":[31,127],"to":[32,89,106,124,128,184],"its":[33,72],"high":[34],"latency":[35],"requirement":[36],"in":[37,74,144,192],"network.":[39],"Nowadays,":[40],"fog":[41],"edge":[43],"been":[45],"popular,":[46],"where":[47],"computation":[48],"occurs":[49],"near":[50],"data":[52],"source":[53,57],"or":[54],"between":[55],"cloud.":[60],"High":[61],"usage":[62],"of":[63,131],"computational":[64,93],"resources":[65,94],"by":[66,95],"incurs":[68],"limited":[69],"room":[70],"deployment":[73],"such":[75],"resource-constrained":[76],"devices.":[77],"with":[81,196],"multiple":[82,103],"exit":[83],"architecture":[84],"are":[85,134],"an":[86,99,149],"optimal":[87],"approach":[88],"preserve":[90],"time":[91],"predicting":[96],"at":[98],"early":[100,104,197],"stage":[101],"using":[102,167],"exits":[105,126],"support":[107],"Edge":[108],"Fog":[110],"Intelligence.":[111],"Early":[112],"exit,":[113],"although":[114],"lightweight":[115],"energy":[117],"efficient,":[118],"mostly":[119],"exhibits":[120],"degraded":[121],"compared":[123],"later":[125],"count":[130],"samples":[132],"that":[133,174],"misclassified.":[135],"To":[136],"overcome":[137],"downfall,":[139],"we":[140],"propose":[141],"uncertainty":[142],"estimation":[143],"loss":[146],"function":[147],"as":[148,187,189],"additional":[150],"parameter":[151],"classification.":[153],"Observational":[154],"on":[156],"CIFAR,":[157],"MNIST,":[158],"human":[159],"lung":[160],"CT":[161],"scan,":[162],"brain":[164],"MRI":[165],"datasets":[166],"VGG-16,":[168],"Lenet-5,":[169],"Resnet":[171],"architectures":[172],"exhibit":[173],"our":[175],"proposed":[176],"model":[177],"is":[178],"better":[179],"than":[180],"existing":[182],"models":[183],"improve":[185],"well":[188],"prediction":[190],"confidence":[191],"Learning":[194],"Models":[195],"exits.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}