{"id":"https://openalex.org/W4394625780","doi":"https://doi.org/10.1109/wacv57701.2024.00118","title":"Grafting Vision Transformers","display_name":"Grafting Vision Transformers","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4394625780","doi":"https://doi.org/10.1109/wacv57701.2024.00118"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00118","pdf_url":null,"source":{"id":"https://openalex.org/S4363607979","display_name":"2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.15943","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101938959","display_name":"Jongwoo Park","orcid":"https://orcid.org/0009-0006-7558-3804"},"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":"Jongwoo Park","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/A5077247727","display_name":"Kumara Kahatapitiya","orcid":"https://orcid.org/0000-0003-4089-2288"},"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":"Kumara Kahatapitiya","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/A5100454683","display_name":"Donghyun Kim","orcid":"https://orcid.org/0000-0002-7132-4454"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donghyun Kim","raw_affiliation_strings":["MIT-IBM Watson AI Lab"],"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862118","display_name":"Shivchander Sudalairaj","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivchander Sudalairaj","raw_affiliation_strings":["MIT-IBM Watson AI Lab"],"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114069812","display_name":"Quanfu Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Quanfu Fan","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084829008","display_name":"Michael S. Ryoo","orcid":"https://orcid.org/0000-0002-5452-8332"},"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":"Michael S. Ryoo","raw_affiliation_strings":["Stony Brook University"],"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":{"min":0,"max":84},"biblio":{"volume":null,"issue":null,"first_page":"1134","last_page":"1143"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.2337,"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":0.2337,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5179443},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.393805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38613415}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00118","pdf_url":null,"source":{"id":"https://openalex.org/S4363607979","display_name":"2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2210.15943","pdf_url":"https://arxiv.org/pdf/2210.15943","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2210.15943","pdf_url":"https://arxiv.org/pdf/2210.15943","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":31,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2737258237","https://openalex.org/W2752782242","https://openalex.org/W2952122856","https://openalex.org/W2963163009","https://openalex.org/W2963446712","https://openalex.org/W2981413347","https://openalex.org/W2982083293","https://openalex.org/W3094502228","https://openalex.org/W3106250896","https://openalex.org/W3121523901","https://openalex.org/W3128633047","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3139633126","https://openalex.org/W3151130473","https://openalex.org/W3190492058","https://openalex.org/W4212774754","https://openalex.org/W4214636423","https://openalex.org/W4246193833","https://openalex.org/W4281756776","https://openalex.org/W4297775537","https://openalex.org/W4308558335","https://openalex.org/W4312769131","https://openalex.org/W4312820606","https://openalex.org/W4312950730","https://openalex.org/W4313007769","https://openalex.org/W4320459518"],"related_works":["https://openalex.org/W3116076068","https://openalex.org/W2951359407","https://openalex.org/W2775347418","https://openalex.org/W2772917594","https://openalex.org/W2755342338","https://openalex.org/W2229312674","https://openalex.org/W2166024367","https://openalex.org/W2079911747","https://openalex.org/W2058170566","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Vision":[0],"Transformers":[1],"(ViTs)":[2],"have":[3],"recently":[4],"become":[5],"the":[6,42,77,88,100,105,144],"state-of-the-art":[7],"across":[8],"many":[9],"computer":[10],"vision":[11],"tasks.":[12],"In":[13,56,132],"contrast":[14],"to":[15,156],"convolutional":[16],"networks":[17],"(CNNs),":[18],"ViTs":[19],"enable":[20],"global":[21,71],"information":[22,75],"sharing":[23],"even":[24],"within":[25],"shallow":[26],"layers":[27],"of":[28,44,90,99,104],"a":[29,61],"network,":[30,78],"i.e.,":[31],"among":[32],"high-resolution":[33],"features.":[34],"However,":[35],"this":[36,57],"perk":[37],"was":[38],"later":[39],"overlooked":[40],"with":[41],"success":[43],"pyramid":[45,126],"architectures":[46],"such":[47],"as":[48],"Swin":[49],"Transformer,":[50],"which":[51,115],"show":[52],"better":[53],"performance-complexity":[54],"trade-offs.":[55],"paper,":[58],"we":[59],"present":[60],"simple":[62],"and":[63,73,82,96,102,119,125,128,151,159,164],"efficient":[64],"add-on":[65],"component":[66],"(termed":[67],"GrafT)":[68],"that":[69],"considers":[70],"dependencies":[72],"multi-scale":[74],"throughout":[76],"in":[79],"both":[80,117,123],"high-":[81],"low-resolution":[83],"features":[84],"alike.":[85],"It":[86],"has":[87],"flexibility":[89],"branching":[91],"out":[92],"at":[93,167],"arbitrary":[94],"depths":[95],"shares":[97],"most":[98],"parameters":[101],"computations":[103],"backbone.":[106],"GrafT":[107,147],"shows":[108],"consistent":[109],"gains":[110],"over":[111],"various":[112,129],"well-known":[113],"models":[114,138,165],"includes":[116],"hybrid":[118],"pure":[120],"Transformer":[121],"types,":[122],"homogeneous":[124],"structures,":[127],"self-attention":[130],"methods.":[131],"particular,":[133],"it":[134],"largely":[135],"benefits":[136],"mobile-size":[137],"by":[139],"providing":[140],"high-level":[141],"semantics.":[142],"On":[143],"ImageNet-1k":[145],"dataset,":[146],"delivers":[148],"+3.9%,":[149],"+1.4%,":[150],"+1.9%":[152],"top-1":[153],"accuracy":[154],"improvement":[155],"DeiT-T,":[157],"Swin-T,":[158],"MobViTXXS,":[160],"respectively.":[161],"Our":[162],"code":[163],"are":[166],"https://github.com/jongwoopark7978/Grafting-Vision-Transformer.":[168]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4394625780","counts_by_year":[],"updated_date":"2024-12-05T02:09:43.485648","created_date":"2024-04-10"}