{"id":"https://openalex.org/W2586565528","doi":"https://doi.org/10.1145/3007192","title":"Energy-Efficient and Improved Image Recognition with Conditional Deep Learning","display_name":"Energy-Efficient and Improved Image Recognition with Conditional Deep Learning","publication_year":2017,"publication_date":"2017-02-09","ids":{"openalex":"https://openalex.org/W2586565528","doi":"https://doi.org/10.1145/3007192","mag":"2586565528"},"language":"en","primary_location":{"id":"doi:10.1145/3007192","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3007192","pdf_url":null,"source":{"id":"https://openalex.org/S96198239","display_name":"ACM Journal on Emerging Technologies in Computing Systems","issn_l":"1550-4832","issn":["1550-4832","1550-4840"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Journal on Emerging Technologies in Computing Systems","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/A5050310538","display_name":"Priyadarshini Panda","orcid":"https://orcid.org/0000-0002-4167-6782"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Priyadarshini Panda","raw_affiliation_strings":["Purdue University, West Lafayette, IN"],"raw_orcid":"https://orcid.org/0000-0002-4167-6782","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032635465","display_name":"Abhronil Sengupta","orcid":"https://orcid.org/0000-0002-5545-4494"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhronil Sengupta","raw_affiliation_strings":["Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031161187","display_name":"Kaushik Roy","orcid":"https://orcid.org/0009-0002-3375-2877"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik Roy","raw_affiliation_strings":["Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050310538"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":1.1093,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.86042316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"13","issue":"3","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9988999962806702,"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/mnist-database","display_name":"MNIST database","score":0.9498229026794434},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7912254333496094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7503307461738586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6903631687164307},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6808197498321533},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5106502175331116},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47677022218704224},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4599079489707947},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.43814557790756226},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37924569845199585},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25995463132858276}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.9498229026794434},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7912254333496094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503307461738586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6903631687164307},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6808197498321533},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5106502175331116},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47677022218704224},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4599079489707947},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.43814557790756226},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37924569845199585},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25995463132858276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3007192","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3007192","pdf_url":null,"source":{"id":"https://openalex.org/S96198239","display_name":"ACM Journal on Emerging Technologies in Computing Systems","issn_l":"1550-4832","issn":["1550-4832","1550-4840"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Journal on Emerging Technologies in Computing Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8899999856948853,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W753012316","https://openalex.org/W1487583988","https://openalex.org/W1533861849","https://openalex.org/W1583837637","https://openalex.org/W1677182931","https://openalex.org/W1815076433","https://openalex.org/W1904365287","https://openalex.org/W1998305460","https://openalex.org/W2060969833","https://openalex.org/W2062118960","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2134557905","https://openalex.org/W2136922672","https://openalex.org/W2141125852","https://openalex.org/W2147768505","https://openalex.org/W2149933564","https://openalex.org/W2160815625","https://openalex.org/W2168231600","https://openalex.org/W2187281534","https://openalex.org/W2194775991","https://openalex.org/W2213612645","https://openalex.org/W2267244539","https://openalex.org/W2293078015","https://openalex.org/W2294059674","https://openalex.org/W2335728318","https://openalex.org/W2546302380","https://openalex.org/W2618530766","https://openalex.org/W3118608800","https://openalex.org/W4231109964","https://openalex.org/W4299828299"],"related_works":["https://openalex.org/W3036048022","https://openalex.org/W4309224979","https://openalex.org/W3026879719","https://openalex.org/W4226493464","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W2911497689","https://openalex.org/W2952813363","https://openalex.org/W4206451978"],"abstract_inverted_index":{"Deep-learning":[0],"neural":[1],"networks":[2,221],"have":[3],"proven":[4],"to":[5,110,152,172,218,244],"be":[6,30,87,157],"very":[7,91],"successful":[8],"for":[9,49,140,195],"a":[10,69,80,83,134],"wide":[11],"range":[12],"of":[13,39,52,72,79,117,126,137,148,182],"recognition":[14,51],"tasks":[15],"across":[16,63],"modern":[17],"computing":[18],"platforms.":[19],"However,":[20],"the":[21,44,50,58,75,104,112,115,123,127,146,149,160,170,175,180,183,215,228,234,248],"computational":[22,77,176],"requirements":[23],"associated":[24],"with":[25,90,199,224],"such":[26],"deep":[27],"nets":[28],"can":[29,86,156],"quite":[31],"high,":[32],"and":[33,120,144],"hence":[34],"their":[35],"energy-efficient":[36],"implementation":[37],"is":[38,47],"great":[40],"interest.":[41],"Although,":[42],"traditionally,":[43],"entire":[45],"network":[46,136,151,171],"utilized":[48],"all":[53],"inputs,":[54],"we":[55,97],"observe":[56],"that":[57],"classification":[59,155,189,262],"difficulty":[60,116,181],"varies":[61],"widely":[62],"inputs":[64,73],"in":[65,114,247,260],"real-world":[66],"datasets;":[67],"only":[68],"small":[70],"fraction":[71],"requires":[74],"full":[76],"effort":[78,177],"network,":[81],"while":[82,186],"large":[84],"majority":[85],"classified":[88],"correctly":[89],"low":[92],"effort.":[93],"In":[94],"this":[95,131],"article,":[96],"propose":[98],"Conditional":[99],"Deep":[100],"Learning":[101],"(CDL),":[102],"where":[103],"convolutional":[105,142,236],"layer":[106,143],"features":[107],"are":[108,203],"used":[109],"identify":[111],"variability":[113],"input":[118,184],"instances":[119],"conditionally":[121],"activate":[122],"deeper":[124],"layers":[125],"network.":[128],"We":[129,212],"achieve":[130],"by":[132],"cascading":[133],"linear":[135,150],"output":[138,147,230],"neurons":[139,231],"each":[141],"monitoring":[145],"decide":[153],"whether":[154],"terminated":[158],"at":[159,233],"current":[161],"stage":[162],"or":[163],"not.":[164],"The":[165,191],"proposed":[166,239],"methodology":[167],"thus":[168],"enables":[169],"dynamically":[173],"adjust":[174],"depending":[178],"on":[179,257],"data":[185],"maintaining":[187],"competitive":[188],"accuracy.":[190],"overall":[192],"energy":[193],"benefits":[194],"MNIST/CIFAR10/Tiny":[196],"ImageNet":[197],"datasets":[198],"state-of-the-art":[200,264],"deep-learning":[201,220],"architectures":[202],"1.84":[204],"\u00d7":[205,207,209],"/2.83":[206],"/4.02":[208],",":[210],"respectively.":[211],"further":[213],"employ":[214],"conditional":[216],"approach":[217],"train":[219],"from":[222,227],"scratch":[223],"integrated":[225,240],"supervision":[226],"additional":[229],"appended":[232],"intermediate":[235],"layers.":[237],"Our":[238],"CDL":[241],"training":[242],"leads":[243],"an":[245],"improvement":[246],"gradient":[249],"convergence":[250],"behavior":[251],"giving":[252],"substantial":[253],"error":[254],"rate":[255],"reduction":[256],"MNIST/CIFAR-10,":[258],"resulting":[259],"improved":[261],"over":[263],"baseline":[265],"networks.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}