{"id":"https://openalex.org/W4385801313","doi":"https://doi.org/10.1109/cvprw59228.2023.00496","title":"DeCAtt: Efficient Vision Transformers with Decorrelated Attention Heads","display_name":"DeCAtt: Efficient Vision Transformers with Decorrelated Attention Heads","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4385801313","doi":"https://doi.org/10.1109/cvprw59228.2023.00496"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw59228.2023.00496","pdf_url":null,"source":{"id":"https://openalex.org/S4363607748","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5033610898","display_name":"Mayukh Bhattacharyya","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mayukh Bhattacharyya","raw_affiliation_strings":["Stony Brook University"],"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013857985","display_name":"Soumitri Chattopadhyay","orcid":"https://orcid.org/0000-0002-2647-6053"},"institutions":[{"id":"https://openalex.org/I170979836","display_name":"Jadavpur University","ror":"https://ror.org/02af4h012","country_code":"IN","type":"education","lineage":["https://openalex.org/I170979836"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Soumitri Chattopadhyay","raw_affiliation_strings":["Jadavpur University"],"affiliations":[{"raw_affiliation_string":"Jadavpur University","institution_ids":["https://openalex.org/I170979836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101977185","display_name":"Sayan Nag","orcid":"https://orcid.org/0000-0001-5652-125X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sayan Nag","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institution_assertions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"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":{"min":0,"max":68},"biblio":{"volume":"abs 1706 3762","issue":null,"first_page":"4695","last_page":"4699"},"is_retracted":false,"is_paratext":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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9985,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9985,"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/overfitting","display_name":"Overfitting","score":0.6445243},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization","score":0.44333634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72014266},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.68877393},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6445243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5087052},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.44333634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41527766},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32861865},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16873798},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1399315},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09751424},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw59228.2023.00496","pdf_url":null,"source":{"id":"https://openalex.org/S4363607748","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.51}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":15,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2095705004","https://openalex.org/W2144513243","https://openalex.org/W2808014987","https://openalex.org/W2963920537","https://openalex.org/W2995128449","https://openalex.org/W3094502228","https://openalex.org/W3121523901","https://openalex.org/W3151130473","https://openalex.org/W3170874841","https://openalex.org/W3190492058","https://openalex.org/W4214636423","https://openalex.org/W4286910290","https://openalex.org/W4293568472","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4387297750","https://openalex.org/W4362597605","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W3009056573","https://openalex.org/W2989932438","https://openalex.org/W2922073769","https://openalex.org/W2490526372","https://openalex.org/W2186333919","https://openalex.org/W1574414179"],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2,31,35,90,97,133,136],"Vision":[3,36],"Transformers":[4,37],"(ViT)":[5],"has":[6],"led":[7],"to":[8,48,73,110],"significant":[9],"performance":[10,127],"gains":[11],"across":[12,65],"various":[13],"computer":[14],"vision":[15,76,104],"tasks":[16],"over":[17,129],"the":[18,23,32,71,95,108,118],"last":[19],"few":[20],"years,":[21],"surpassing":[22],"de":[24],"facto":[25],"standard":[26],"CNN":[27],"architectures.":[28],"However,":[29],"most":[30],"prominent":[33],"variations":[34],"are":[38,46],"resource-intensive":[39],"architectures":[40],"with":[41],"huge":[42],"parameter":[43],"sizes.":[44],"They":[45],"known":[47],"be":[49],"data-hungry":[50],"and":[51,138],"overfit":[52],"quickly":[53],"on":[54,117],"comparatively":[55],"smaller":[56],"datasets.":[57],"Consequently,":[58],"this":[59,79,122],"holds":[60],"back":[61],"their":[62],"widespread":[63],"usage":[64],"low-resource":[66],"settings,":[67],"which":[68,146],"brings":[69],"forth":[70],"need":[72],"develop":[74],"resource-efficient":[75],"transformers.":[77],"To":[78],"end,":[80],"we":[81,141],"introduce":[82],"a":[83,98,103,125,130],"regularization":[84],"loss":[85,123],"that":[86],"prioritizes":[87],"efficient":[88],"utilization":[89],"model":[91],"parameters":[92],"by":[93],"decorrelating":[94],"heads":[96,109],"multi-headed":[99],"attention":[100],"block":[101],"in":[102,143],"transformer.":[105],"This":[106],"forces":[107],"learn":[111],"distinct":[112],"features":[113],"rather":[114],"than":[115],"focus":[116],"same":[119],"ones.":[120],"Using":[121],"provides":[124],"consistent":[126],"improvement":[128],"wide":[131],"range":[132],"varying":[134],"scenarios":[135],"models":[137],"datasets":[139],"as":[140],"show":[142],"our":[144],"experiments,":[145],"proves":[147],"its":[148],"superior":[149],"effectiveness.":[150]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4385801313","counts_by_year":[],"updated_date":"2024-12-14T04:15:44.812349","created_date":"2023-08-15"}