{"id":"https://openalex.org/W7204147172","doi":"https://doi.org/10.1109/access.2026.3726698","title":"E2AM: A Controlled Evaluation Framework for Energy-Aware Training and Deployment of Deep Vision Models","display_name":"E2AM: A Controlled Evaluation Framework for Energy-Aware Training and Deployment of Deep Vision Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204147172","doi":"https://doi.org/10.1109/access.2026.3726698"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3726698","doi":"https://doi.org/10.1109/access.2026.3726698","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3726698","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,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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"},"parent_works":[],"lineage":["https://openalex.org/W7204147172"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3726698","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147989404","display_name":"Satyanarayana Kanulla","orcid":"https://orcid.org/0009-0009-5551-8409","observed_orcids":["https://orcid.org/0009-0009-5551-8409"]},"institutions":[{"id":"https://openalex.org/I4401726783","display_name":"VIT-AP University","ror":"https://ror.org/007v4hf75","country_code":"IN","type":"education","lineage":["https://openalex.org/I4401726783"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Satyanarayana Kanulla","raw_affiliation_strings":["VIT-AP University"],"raw_orcid":"https://orcid.org/0009-0009-5551-8409","affiliations":[{"raw_affiliation_string":"VIT-AP University","institution_ids":["https://openalex.org/I4401726783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146221403","display_name":"Edara Sreenivasa Reddy","orcid":"https://orcid.org/0000-0001-7347-2680","observed_orcids":["https://orcid.org/0000-0001-7347-2680"]},"institutions":[{"id":"https://openalex.org/I4401726783","display_name":"VIT-AP University","ror":"https://ror.org/007v4hf75","country_code":"IN","type":"education","lineage":["https://openalex.org/I4401726783"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Edara Sreenivasa Reddy","raw_affiliation_strings":["VIT-AP University"],"raw_orcid":"https://orcid.org/0000-0001-7347-2680","affiliations":[{"raw_affiliation_string":"VIT-AP University","institution_ids":["https://openalex.org/I4401726783"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5118670763","display_name":"Shanmukesh Bonala","orcid":"https://orcid.org/0009-0008-3651-4077","observed_orcids":["https://orcid.org/0009-0008-3651-4077"]},"institutions":[{"id":"https://openalex.org/I4401726783","display_name":"VIT-AP University","ror":"https://ror.org/007v4hf75","country_code":"IN","type":"education","lineage":["https://openalex.org/I4401726783"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shanmukesh Bonala","raw_affiliation_strings":["VIT-AP University"],"raw_orcid":"https://orcid.org/0009-0008-3651-4077","affiliations":[{"raw_affiliation_string":"VIT-AP University","institution_ids":["https://openalex.org/I4401726783"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4401726783"],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"130202","last_page":"130223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9258000254631042,"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":0.9258000254631042,"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/T12238","display_name":"Green IT and Sustainability","score":0.01860000006854534,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.018200000748038292,"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/energy-efficient-training","display_name":"energy-efficient training","score":0.6420000195503235},{"id":"https://openalex.org/keywords/gradient-accumulation","display_name":"gradient accumulation","score":1.0},{"id":"https://openalex.org/keywords/early-stopping","display_name":"early stopping","score":0.9599999785423279},{"id":"https://openalex.org/keywords/int8-quantization","display_name":"INT8 quantization","score":0.765999972820282},{"id":"https://openalex.org/keywords/model-compression","display_name":"model compression","score":0.4830000102519989},{"id":"https://openalex.org/keywords/resnet-50","display_name":"ResNet50","score":0.6779999732971191},{"id":"https://openalex.org/keywords/efficientnetv2","display_name":"EfficientNetV2","score":0.902999997138977},{"id":"https://openalex.org/keywords/mobilevit","display_name":"MobileViT","score":0.8320000171661377},{"id":"https://openalex.org/keywords/convnext-v2","display_name":"ConvNeXt V2","score":0.8960000276565552}],"concepts":[{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7954000234603882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580999732017517},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7093999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5163999795913696},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3995000123977661},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2732999920845032}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3726698","doi":"https://doi.org/10.1109/access.2026.3726698","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3726698","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,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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:c4fb00ee897f46daaaa1c36405721a97","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/c4fb00ee897f46daaaa1c36405721a97","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,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 130202-130223 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3726698","doi":"https://doi.org/10.1109/access.2026.3726698","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3726698","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,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","ki-jl-1","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"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":[{"score":0.5690000057220459,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2752782242","https://openalex.org/W2777406049","https://openalex.org/W2948223045","https://openalex.org/W2955419283","https://openalex.org/W2963855133","https://openalex.org/W3111917867","https://openalex.org/W3157218387","https://openalex.org/W3170647102","https://openalex.org/W3214897310","https://openalex.org/W4283157527","https://openalex.org/W4283704460","https://openalex.org/W4386076493","https://openalex.org/W4400446288","https://openalex.org/W4401474635","https://openalex.org/W4403390367","https://openalex.org/W4415543913"],"related_works":["https://openalex.org/W7220727147","https://openalex.org/W2982348880","https://openalex.org/W7171641226","https://openalex.org/W2807879038","https://openalex.org/W4413767844","https://openalex.org/W4289827994","https://openalex.org/W4401474635","https://openalex.org/W4415543913","https://openalex.org/W4386412380","https://openalex.org/W6885080249"],"abstract_inverted_index":{"The":[0,87,212,249],"increasing":[1],"energy":[2,122,146],"cost":[3],"of":[4,117,163,185],"training":[5,145,170,293],"deep":[6,18],"vision":[7],"models":[8,106],"has":[9],"made":[10],"computational":[11],"efficiency":[12,296],"an":[13,83,182,244,265],"important":[14],"objective":[15],"in":[16,269],"modern":[17],"learning.":[19],"Although":[20],"tensor":[21],"caching,":[22,70],"automatic":[23],"mixed":[24],"precision":[25],"(AMP),":[26],"gradient":[27,72],"accumulation,":[28,73],"$\\ell":[29,74],"_{1}$":[30,75],"sparsity":[31,76],"regularization,":[32,77],"learning-rate":[33,80],"scheduling,":[34],"pruning,":[35],"and":[36,43,78,92,98,103,120,154,221,228,260,294],"quantization":[37,263],"are":[38,47,54,89,107,202,230],"established":[39],"techniques,":[40],"their":[41],"individual":[42],"cumulative":[44],"accuracy\u2013energy":[45],"effects":[46,297],"difficult":[48],"to":[49,134],"interpret":[50],"when":[51],"several":[52],"factors":[53],"modified":[55],"simultaneously.":[56],"This":[57],"paper":[58],"presents":[59],"E2AM,":[60],"a":[61,113,176,195,287],"controlled,":[62],"hardware-measured":[63],"framework":[64],"for":[65,161,273,291],"evaluating":[66],"five":[67],"training-time":[68],"interventions\u2014tensor":[69],"AMP,":[71],"cosine":[79],"scheduling\u2014together":[81],"with":[82,181],"energy-aware":[84],"early-stopping":[85],"rule.":[86],"interventions":[88],"evaluated":[90,151,193],"individually":[91],"cumulatively":[93],"across":[94,149],"ResNet-50,":[95],"EfficientNetV2-S,":[96],"MobileViTv2,":[97],"ConvNeXtV2-Tiny":[99,172,224],"using":[100,194],"CIFAR-10,":[101],"CIFAR-100,":[102],"Tiny-ImageNet.":[104],"All":[105],"trained":[108],"from":[109,125],"random":[110],"initialization":[111],"under":[112],"common":[114],"maximum":[115],"budget":[116],"50":[118],"epochs,":[119],"GPU-board":[121],"is":[123,192,236],"integrated":[124],"hardware":[126],"power":[127],"telemetry":[128],"over":[129],"180":[130],"logged":[131],"runs.":[132],"Relative":[133],"the":[135,139,150,164,168,198,218,222],"all-off":[136],"reference":[137],"configuration,":[138],"complete":[140],"E2AM":[141,285],"configuration":[142,191,279],"reduces":[143],"measured":[144],"by":[147],"30\u201363%":[148],"architecture\u2013dataset":[152],"pairs":[153,166],"achieves":[155],"higher":[156],"observed":[157,213],"best":[158],"validation":[159],"accuracy":[160,183,200,282],"11":[162],"12":[165],"within":[167],"fixed":[169],"budget.":[171],"on":[173],"CIFAR-10":[174],"provides":[175,264],"lower-energy":[177],"near-iso-accuracy":[178],"operating":[179],"point,":[180],"difference":[184],"\u22120.08":[186],"percentage":[187],"points.":[188],"Because":[189,226],"each":[190],"single":[196],"seed,":[197],"reported":[199],"differences":[201],"interpreted":[203,237],"as":[204,238,243],"descriptive":[205],"operating-point":[206],"comparisons":[207],"rather":[208,241,298],"than":[209,242,299],"inferential":[210],"estimates.":[211],"responses":[214],"also":[215],"differ":[216],"between":[217],"SGD-trained":[219],"architectures":[220],"AdamW-trained":[223],"configuration.":[225],"optimizer":[227,247],"architecture":[229],"not":[231],"independently":[232],"varied,":[233],"this":[234],"behavior":[235],"architecture\u2013optimizer-configuration":[239],"dependence":[240],"isolated":[245],"causal":[246],"effect.":[248],"deployment":[250,295],"analysis":[251],"further":[252],"reports":[253],"post-optimization":[254],"accuracy,":[255],"serialized":[256,270],"artifact":[257,271],"size,":[258],"latency,":[259],"throughput.":[261],"INT8":[262],"approximately":[266],"fourfold":[267],"reduction":[268],"size":[272],"most":[274],"graph-traceable":[275],"configurations,":[276],"whereas":[277],"one":[278],"exhibits":[280],"substantial":[281],"degradation.":[283],"Therefore,":[284],"contributes":[286],"controlled":[288],"evaluation":[289],"methodology":[290],"characterizing":[292],"proposing":[300],"novel":[301],"constituent":[302],"optimization":[303],"techniques.":[304]},"counts_by_year":[],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2026-08-25T00:00:00"}