{"id":"https://openalex.org/W4313066265","doi":"https://doi.org/10.5220/0011578000003335","title":"Number of Attention Heads vs. Number of Transformer-encoders in Computer Vision","display_name":"Number of Attention Heads vs. Number of Transformer-encoders in Computer Vision","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4313066265","doi":"https://doi.org/10.5220/0011578000003335"},"language":"en","primary_location":{"id":"doi:10.5220/0011578000003335","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011578000003335","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0011578000003335","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048555215","display_name":"Tomas Hrycej","orcid":null},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tomas Hrycej","raw_affiliation_strings":["Institute of Computer Science, University of St. Gallen (HSG), St. Gallen, Switzerland, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of St. Gallen (HSG), St. Gallen, Switzerland, --- Select a Country ---","institution_ids":["https://openalex.org/I202963720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045444454","display_name":"Bernhard Bermeitinger","orcid":"https://orcid.org/0000-0002-2524-1850"},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Bernhard Bermeitinger","raw_affiliation_strings":["Institute of Computer Science, University of St. Gallen (HSG), St. Gallen, Switzerland, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of St. Gallen (HSG), St. Gallen, Switzerland, --- Select a Country ---","institution_ids":["https://openalex.org/I202963720"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024322708","display_name":"Siegfried Handschuh","orcid":"https://orcid.org/0000-0002-6195-9034"},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Siegfried Handschuh","raw_affiliation_strings":["Institute of Computer Science, University of St. Gallen (HSG), St. Gallen, Switzerland, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of St. Gallen (HSG), St. Gallen, Switzerland, --- Select a Country ---","institution_ids":["https://openalex.org/I202963720"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I202963720"],"apc_list":null,"apc_paid":null,"fwci":0.6471,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7935494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"315","last_page":"321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9972000122070312,"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/transformer","display_name":"Transformer","score":0.7232221961021423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6072710752487183},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5299694538116455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48467162251472473},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.36076611280441284},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35471242666244507},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3512004613876343},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15879717469215393},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15068000555038452},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06908643245697021}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7232221961021423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6072710752487183},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5299694538116455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48467162251472473},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.36076611280441284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35471242666244507},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3512004613876343},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15879717469215393},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15068000555038452},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06908643245697021},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0011578000003335","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011578000003335","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:www.alexandria.unisg.ch:267726","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400650","display_name":"Alexandria (UniSG) (University of St.Gallen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210158813","host_organization_name":"St.Gallen University of Teacher Education","host_organization_lineage":["https://openalex.org/I4210158813"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Journal paper"},{"id":"pmh:oai:arXiv.org:2209.07221","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.07221","pdf_url":"https://arxiv.org/pdf/2209.07221","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.5220/0011578000003335","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011578000003335","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W2112796928","https://openalex.org/W2163605009","https://openalex.org/W2732026016","https://openalex.org/W2908510526","https://openalex.org/W3094502228","https://openalex.org/W3118608800","https://openalex.org/W4205460645"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Determining":[0],"an":[1,20],"appropriate":[2],"number":[3,12,40,51,57,74,79,111,145],"of":[4,13,41,48,52,58,75,80,88,112,136,146,153],"attention":[5],"heads":[6,76,113,147],"on":[7,15,127,141],"one":[8,116],"hand":[9],"and":[10,77],"the":[11,16,29,35,38,46,56,69,73,78,86,128,131,134,144],"transformer-encoders,":[14],"other":[17,142],"hand,":[18],"is":[19,102,148],"important":[21,150],"choice":[22],"for":[23],"Computer":[24],"Vision":[25],"(CV)":[26],"tasks":[27],"using":[28],"Transformer":[30],"architecture.":[31],"Computing":[32],"experiments":[33],"confirmed":[34],"expectation":[36],"that":[37,152],"total":[39],"parameters":[42],"has":[43],"to":[44,92,98,104],"satisfy":[45],"condition":[47],"overdetermination":[49],"(i.e.,":[50,133],"constraints":[53],"significantly":[54],"exceeding":[55],"parameters).":[59],"Then,":[60],"good":[61],"generalization":[62],"performance":[63],"can":[64,82,95],"be":[65,83,93,96,99],"expected.":[66],"This":[67],"sets":[68],"boundaries":[70],"within":[71,130],"which":[72],"transformers":[81,107],"chosen.":[84],"If":[85],"role":[87],"context":[89,129],"in":[90],"images":[91],"classified":[94],"assumed":[97],"small,":[100],"it":[101],"favorable":[103],"use":[105],"multiple":[106],"with":[108],"a":[109,137],"low":[110],"(such":[114],"as":[115,151],"or":[117],"two).":[118],"In":[119],"classifying":[120],"objects":[121],"whose":[122],"class":[123],"may":[124],"heavily":[125],"depend":[126],"image":[132],"meaning":[135],"patch":[138],"being":[139],"dependent":[140],"patches),":[143],"equally":[149],"transformers.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}
