{"id":"https://openalex.org/W3135012968","doi":"https://doi.org/10.1109/access.2021.3064819","title":"ResNet Autoencoders for Unsupervised Feature Learning From High-Dimensional Data: Deep Models Resistant to Performance Degradation","display_name":"ResNet Autoencoders for Unsupervised Feature Learning From High-Dimensional Data: Deep Models Resistant to Performance Degradation","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3135012968","doi":"https://doi.org/10.1109/access.2021.3064819","mag":"3135012968"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3064819","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3064819","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09373350.pdf","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://ieeexplore.ieee.org/ielx7/6287639/9312710/09373350.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031428916","display_name":"Chathurika S. Wickramasinghe","orcid":"https://orcid.org/0000-0002-3333-5101"},"institutions":[{"id":"https://openalex.org/I184840846","display_name":"Virginia Commonwealth University","ror":"https://ror.org/02nkdxk79","country_code":"US","type":"education","lineage":["https://openalex.org/I184840846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chathurika S. Wickramasinghe","raw_affiliation_strings":["Virginia Commonwealth University, Richmond, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3333-5101","affiliations":[{"raw_affiliation_string":"Virginia Commonwealth University, Richmond, VA, USA","institution_ids":["https://openalex.org/I184840846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062404663","display_name":"Daniel Marino","orcid":"https://orcid.org/0000-0002-8686-4752"},"institutions":[{"id":"https://openalex.org/I184840846","display_name":"Virginia Commonwealth University","ror":"https://ror.org/02nkdxk79","country_code":"US","type":"education","lineage":["https://openalex.org/I184840846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel L. Marino","raw_affiliation_strings":["Virginia Commonwealth University, Richmond, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Commonwealth University, Richmond, VA, USA","institution_ids":["https://openalex.org/I184840846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032679061","display_name":"Milos Manic","orcid":"https://orcid.org/0000-0003-1484-7678"},"institutions":[{"id":"https://openalex.org/I184840846","display_name":"Virginia Commonwealth University","ror":"https://ror.org/02nkdxk79","country_code":"US","type":"education","lineage":["https://openalex.org/I184840846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milos Manic","raw_affiliation_strings":["Virginia Commonwealth University, Richmond, VA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1484-7678","affiliations":[{"raw_affiliation_string":"Virginia Commonwealth University, Richmond, VA, USA","institution_ids":["https://openalex.org/I184840846"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184840846"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":5.4646,"has_fulltext":true,"cited_by_count":77,"citation_normalized_percentile":{"value":0.96910126,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"9","issue":null,"first_page":"40511","last_page":"40520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8783499002456665},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7894710898399353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7874695062637329},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.7377815246582031},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6973348259925842},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6636176109313965},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6326430439949036},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5650591850280762},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5543729066848755},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5215063691139221},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5210344791412354},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4924980103969574}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8783499002456665},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7894710898399353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7874695062637329},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.7377815246582031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973348259925842},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6636176109313965},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6326430439949036},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5650591850280762},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5543729066848755},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5215063691139221},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5210344791412354},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4924980103969574},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3064819","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3064819","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09373350.pdf","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:bb588ac372eb4dafb062b8bbc0048526","is_oa":true,"landing_page_url":"https://doaj.org/article/bb588ac372eb4dafb062b8bbc0048526","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 9, Pp 40511-40520 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3064819","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3064819","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09373350.pdf","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135012968.pdf","grobid_xml":"https://content.openalex.org/works/W3135012968.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1026270304","https://openalex.org/W1562753845","https://openalex.org/W1576462183","https://openalex.org/W1837656155","https://openalex.org/W2025485599","https://openalex.org/W2026430219","https://openalex.org/W2066043610","https://openalex.org/W2087016914","https://openalex.org/W2099242680","https://openalex.org/W2099471712","https://openalex.org/W2100495367","https://openalex.org/W2152540970","https://openalex.org/W2177066871","https://openalex.org/W2194775991","https://openalex.org/W2219715551","https://openalex.org/W2302255633","https://openalex.org/W2324044936","https://openalex.org/W2324488761","https://openalex.org/W2480364715","https://openalex.org/W2546191734","https://openalex.org/W2577946330","https://openalex.org/W2601686579","https://openalex.org/W2603986758","https://openalex.org/W2736470268","https://openalex.org/W2750384547","https://openalex.org/W2767547957","https://openalex.org/W2780433069","https://openalex.org/W2783675117","https://openalex.org/W2784962210","https://openalex.org/W2791512297","https://openalex.org/W2792800544","https://openalex.org/W2797465556","https://openalex.org/W2897197428","https://openalex.org/W2907804426","https://openalex.org/W2919115771","https://openalex.org/W2946844671","https://openalex.org/W2950621961","https://openalex.org/W2952626150","https://openalex.org/W2963446712","https://openalex.org/W3018960895","https://openalex.org/W3101623935","https://openalex.org/W3118608800","https://openalex.org/W4320013936","https://openalex.org/W4366961264","https://openalex.org/W6626481562","https://openalex.org/W6633816495","https://openalex.org/W6687483927","https://openalex.org/W6698183232","https://openalex.org/W6732248266","https://openalex.org/W6734171162","https://openalex.org/W6743688258","https://openalex.org/W6747673963","https://openalex.org/W6748483046","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W4394785709","https://openalex.org/W4296978181","https://openalex.org/W2912987408","https://openalex.org/W3004801820","https://openalex.org/W4281672036","https://openalex.org/W4313444753","https://openalex.org/W4230582276","https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W2937381246"],"abstract_inverted_index":{"Efficient":[0],"modeling":[1],"of":[2,60,100,122,140,195,206,227],"high-dimensional":[3],"data":[4,39],"requires":[5],"extracting":[6],"only":[7],"relevant":[8],"dimensions":[9],"through":[10],"feature":[11,14,52,96,126,146,163,240],"learning.":[12,97],"Unsupervised":[13],"learning":[15,127,164,241],"has":[16],"gained":[17],"tremendous":[18],"attention":[19],"due":[20,75],"to":[21,36,76,80,110,129,155,172,213,216],"its":[22,90],"unbiased":[23],"approach,":[24],"no":[25],"need":[26],"for":[27,50,94,114,124],"prior":[28],"knowledge":[29],"or":[30],"expensive":[31],"manual":[32],"processing,":[33],"and":[34,89,102,134,148,175,178,188,224,235,250],"ability":[35],"handle":[37],"exponential":[38],"growth.":[40],"Deep":[41],"Autoencoder":[42,87],"(AE)":[43],"is":[44,104],"a":[45,58],"state-of-the-art":[46],"deep":[47],"neural":[48],"network":[49,67,116],"unsupervised":[51,95,125,149],"learning,":[53,150],"which":[54],"learns":[55],"embedded-representations":[56,72],"using":[57],"series":[59],"stacked":[61],"layers.":[62],"However,":[63],"as":[64,143],"the":[65,108,120,138,193,254],"AE":[66,199,214],"gets":[68],"deeper,":[69],"these":[70],"learned":[71,170],"can":[73],"deteriorate":[74],"vanishing":[77],"gradient,":[78],"leading":[79],"performance":[81,204],"degradation.":[82],"This":[83],"article":[84],"presents":[85],"ResNet":[86],"(RAE)":[88],"convolutional":[91],"version":[92],"(C-RAE)":[93],"The":[98],"advantage":[99],"RAE":[101,133,174,177,234],"C-RAE":[103,135,179,197,219,236,252],"that":[105],"it":[106],"enables":[107],"user":[109],"add":[111],"residual":[112],"connections":[113],"increased":[115],"capacity":[117],"without":[118,159],"incurring":[119],"cost":[121],"degradation":[123,205],"compared":[128,181,212],"standard":[130,230],"AEs.":[131],"While":[132],"inherit":[136],"all":[137],"advantages":[139],"AEs,":[141],"such":[142],"automated":[144],"non-linear":[145],"extraction":[147],"they":[151],"also":[152],"allow":[153],"users":[154],"design":[156],"larger":[157],"networks":[158],"adverse":[160],"effects":[161],"on":[162,169,184],"performance.":[165],"We":[166],"performed":[167],"classification":[168,207],"embedded-representation":[171],"evaluate":[173],"C-RAE.":[176],"were":[180],"against":[182],"AEs":[183],"MNIST,":[185,187],"Fashion":[186],"CIFAR10":[189],"datasets.":[190],"When":[191,232],"increasing":[192],"number":[194],"layers,":[196],"outperformed":[198],"by":[200],"showing":[201],"significantly":[202],"lower":[203,225],"accuracy":[208,223,228],"(less":[209],"than":[210,229],"3%)":[211],"(33%":[215],"65%).":[217],"Further,":[218],"exhibited":[220],"higher":[221],"mean":[222],"variance":[226],"AE.":[231],"comparing":[233],"with":[237],"widely":[238],"used":[239],"methods":[242],"(Convolutional":[243],"AE,":[244],"PCA,":[245],"ICA,":[246],"LLE,":[247],"Factor":[248],"Analysis,":[249],"SVD),":[251],"showed":[253],"highest":[255],"accuracy.":[256]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}