{"id":"https://openalex.org/W4205377807","doi":"https://doi.org/10.1109/access.2021.3133200","title":"Self-Supervised Representation Learning for Document Image Classification","display_name":"Self-Supervised Representation Learning for Document Image Classification","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W4205377807","doi":"https://doi.org/10.1109/access.2021.3133200"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3133200","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3133200","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09638456.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/ielx7/6287639/6514899/09638456.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053635416","display_name":"Shoaib Ahmed Siddiqui","orcid":"https://orcid.org/0000-0003-4600-7331"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Shoaib Ahmed Siddiqui","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany and TU Kaiserslautern, Kaiserslautern, Germany. (e-mail: shoaib_ahmed.siddiqui@dfki.de)","TU Kaiserslautern, Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany and TU Kaiserslautern, Kaiserslautern, Germany. (e-mail: shoaib_ahmed.siddiqui@dfki.de)","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I153267046"]},{"raw_affiliation_string":"TU Kaiserslautern, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I153267046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101904182","display_name":"Andreas Dengel","orcid":"https://orcid.org/0000-0002-6100-8255"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Dengel","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany and TU Kaiserslautern, Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany and TU Kaiserslautern, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026","https://openalex.org/I153267046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058813180","display_name":"Sheraz Ahmed","orcid":"https://orcid.org/0000-0002-4239-6520"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sheraz Ahmed","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany"],"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053635416"],"corresponding_institution_ids":["https://openalex.org/I153267046","https://openalex.org/I33256026"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.9797,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81364301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"9","issue":null,"first_page":"164358","last_page":"164367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955999851226807,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955999851226807,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9886999726295471,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9758999943733215,"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/computer-science","display_name":"Computer science","score":0.7901793718338013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7514455318450928},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6027362942695618},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.5811514854431152},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5794833898544312},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5563235282897949},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5325065851211548},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.520687460899353},{"id":"https://openalex.org/keywords/linear-classifier","display_name":"Linear classifier","score":0.5159248113632202},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5054535865783691},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4361022710800171},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22716861963272095},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20684444904327393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901793718338013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7514455318450928},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6027362942695618},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.5811514854431152},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5794833898544312},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5563235282897949},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5325065851211548},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.520687460899353},{"id":"https://openalex.org/C139532973","wikidata":"https://www.wikidata.org/wiki/Q2679259","display_name":"Linear classifier","level":3,"score":0.5159248113632202},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5054535865783691},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4361022710800171},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22716861963272095},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20684444904327393},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3133200","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3133200","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09638456.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:bee32c8c8066413ea4cbf7fd1dbcc5d3","is_oa":true,"landing_page_url":"https://doaj.org/article/bee32c8c8066413ea4cbf7fd1dbcc5d3","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"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 164358-164367 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3133200","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3133200","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09638456.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":[{"display_name":"Good health and well-being","score":0.75,"id":"https://metadata.un.org/sdg/3"}],"awards":[{"id":"https://openalex.org/G638475303","display_name":null,"funder_award_id":"NVAIL","funder_id":"https://openalex.org/F4320309480","funder_display_name":"Nvidia"},{"id":"https://openalex.org/G7225624288","display_name":null,"funder_award_id":"This work was","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G8669804435","display_name":null,"funder_award_id":"01IW17002","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4205377807.pdf","grobid_xml":"https://content.openalex.org/works/W4205377807.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W205301110","https://openalex.org/W343636949","https://openalex.org/W1510710711","https://openalex.org/W1649885719","https://openalex.org/W1686810756","https://openalex.org/W2004665841","https://openalex.org/W2028571532","https://openalex.org/W2031408949","https://openalex.org/W2079017068","https://openalex.org/W2097624458","https://openalex.org/W2098345386","https://openalex.org/W2117539524","https://openalex.org/W2144796873","https://openalex.org/W2156332201","https://openalex.org/W2162262658","https://openalex.org/W2194775991","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2493916176","https://openalex.org/W2515936484","https://openalex.org/W2594633041","https://openalex.org/W2605976347","https://openalex.org/W2618530766","https://openalex.org/W2769937543","https://openalex.org/W2785325870","https://openalex.org/W2786162033","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2901890385","https://openalex.org/W2944828972","https://openalex.org/W2962772269","https://openalex.org/W2963446712","https://openalex.org/W2964137095","https://openalex.org/W2964350391","https://openalex.org/W2988736778","https://openalex.org/W3003981162","https://openalex.org/W3004127423","https://openalex.org/W3004240503","https://openalex.org/W3005680577","https://openalex.org/W3022061250","https://openalex.org/W3035060554","https://openalex.org/W3035251701","https://openalex.org/W3035524453","https://openalex.org/W3080523870","https://openalex.org/W3093122194","https://openalex.org/W3101483505","https://openalex.org/W3108655343","https://openalex.org/W3110446398","https://openalex.org/W3134652006","https://openalex.org/W4287812705","https://openalex.org/W4292779060","https://openalex.org/W4293861706","https://openalex.org/W4294170691","https://openalex.org/W4297808394","https://openalex.org/W6608326786","https://openalex.org/W6630471269","https://openalex.org/W6637373629","https://openalex.org/W6682691769","https://openalex.org/W6694260854","https://openalex.org/W6701655646","https://openalex.org/W6734194636","https://openalex.org/W6739575509","https://openalex.org/W6747899497","https://openalex.org/W6755207826","https://openalex.org/W6763442200","https://openalex.org/W6770514103","https://openalex.org/W6774314701","https://openalex.org/W6776700526","https://openalex.org/W6777265123","https://openalex.org/W6778883912","https://openalex.org/W6779326418","https://openalex.org/W6784015424","https://openalex.org/W6791742336"],"related_works":["https://openalex.org/W1586607209","https://openalex.org/W122912556","https://openalex.org/W4312414840","https://openalex.org/W2621411691","https://openalex.org/W2271357838","https://openalex.org/W2556866732","https://openalex.org/W2328989934","https://openalex.org/W2348322200","https://openalex.org/W2270788204","https://openalex.org/W1434866090"],"abstract_inverted_index":{"Supervised":[0],"learning,":[1],"despite":[2],"being":[3],"extremely":[4],"effective,":[5],"relies":[6],"on":[7,102,136,161],"expensive,":[8],"time-consuming,":[9],"and":[10,129,201],"error-prone":[11],"annotations.":[12],"Self-supervised":[13],"learning":[14,24,100,245],"has":[15],"recently":[16],"emerged":[17],"as":[18,31,149],"a":[19,26,33,112,133,212,248,265],"strong":[20],"alternate":[21],"to":[22,54,89,118,151,176],"supervised":[23,75,203],"in":[25,87,144,174,187,197,215,256,268],"range":[27],"of":[28,36,71,138,147,172,190,224,259],"different":[29,125],"domains":[30],"collecting":[32],"large":[34,103],"amount":[35,223],"unlabeled":[37],"data":[38,225],"can":[39,93],"be":[40,94],"achieved":[41],"by":[42,59],"simply":[43],"crawling":[44],"the":[45,69,154,179,188,227,230,257],"internet.":[46],"These":[47],"self-supervised":[48,90,98,139,165,200,243],"methods":[49,101,127],"automatically":[50],"discover":[51],"features":[52],"relevant":[53],"represent":[55],"an":[56,145,170,221],"input":[57],"example":[58],"using":[60,97,123,164,242],"self-defined":[61],"proxy":[62],"tasks.":[63],"In":[64],"this":[65,108,194,216],"paper,":[66],"we":[67,110],"question":[68],"potential":[70],"commonly":[72],"employed":[73],"purely":[74],"training":[76],"(starting":[77],"either":[78],"from":[79,141,153,167,178,234],"ImageNet":[80,156,181],"pretrained":[81,157,182,209],"networks":[82],"or":[83],"pure":[84],"random":[85],"initialization)":[86],"contrast":[88,175],"representations":[91,240],"that":[92,186,239],"learned":[95,241],"directly":[96],"representation":[99,244],"document":[104,114,252],"image":[105,115,121,253],"datasets.":[106],"For":[107],"purpose,":[109],"leverage":[111],"large-scale":[113],"collection":[116],"(RVL-CDIP)":[117],"train":[119],"ResNet-50":[120,142,168],"encoder":[122],"two":[124],"self-supervision":[126],"(SimCLR":[128],"Barlow":[130],"Twins).":[131],"Employing":[132],"linear":[134],"classifier":[135],"top":[137],"embeddings":[140,166],"results":[143,237],"accuracy":[146,171],"86.75%":[148],"compared":[150],"71.43%":[152],"corresponding":[155,180],"embeddings.":[158,183],"Similarly,":[159],"evaluating":[160],"Tobacco-3482":[162],"dataset":[163],"yields":[169],"88.52%":[173],"74.16%":[177],"We":[184],"show":[185,238],"case":[189,228],"limited":[191,260],"labeled":[192,261],"data,":[193,262],"wide":[195],"gap":[196,217],"performance":[198],"between":[199],"fully":[202],"models":[204],"persists":[205],"even":[206],"after":[207],"fine-tuning":[208],"models.":[210],"However,":[211],"significant":[213],"reduction":[214],"is":[218,232,264],"observed":[219],"with":[220],"increasing":[222],"including":[226],"where":[229],"model":[231],"trained":[233],"scratch.":[235],"Our":[236],"techniques":[246],"are":[247],"viable":[249],"option":[250],"for":[251],"classification,":[254],"specifically":[255],"context":[258],"which":[263],"usual":[266],"restriction":[267],"industrial":[269],"use":[270],"cases.":[271]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}