{"id":"https://openalex.org/W4378474357","doi":"https://doi.org/10.48550/arxiv.2305.15272","title":"ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers","display_name":"ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers","publication_year":2023,"publication_date":"2023-05-24","ids":{"openalex":"https://openalex.org/W4378474357","doi":"https://doi.org/10.48550/arxiv.2305.15272"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.15272","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.15272","pdf_url":"https://arxiv.org/pdf/2305.15272","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":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.15272","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110981770","display_name":"Jingfeng Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yao, Jingfeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037191476","display_name":"Xinggang Wang","orcid":"https://orcid.org/0000-0001-6732-7823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xinggang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004788654","display_name":"Shusheng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Shusheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101902183","display_name":"Baoyuan Wang","orcid":"https://orcid.org/0000-0002-8268-7517"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Baoyuan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110981770"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","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/T11019","display_name":"Image Enhancement Techniques","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9957000017166138,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9926999807357788,"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":0.7078580856323242},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6498368978500366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6301909685134888},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5451374650001526},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5325525999069214},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5299683213233948},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4958275258541107},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.42802584171295166},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.42436912655830383},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31153446435928345},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11066830158233643},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1029658317565918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7078580856323242},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6498368978500366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6301909685134888},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5451374650001526},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5325525999069214},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5299683213233948},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4958275258541107},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42802584171295166},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.42436912655830383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31153446435928345},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11066830158233643},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1029658317565918},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.15272","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.15272","pdf_url":"https://arxiv.org/pdf/2305.15272","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":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.15272","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.15272","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.15272","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.15272","pdf_url":"https://arxiv.org/pdf/2305.15272","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":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.6200000047683716,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378474357.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W2378211422","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"Recently,":[0],"plain":[1],"vision":[2,12],"Transformers":[3],"(ViTs)":[4],"have":[5,25],"shown":[6],"impressive":[7],"performance":[8,166],"on":[9,121,150],"various":[10,137],"computer":[11],"tasks,":[13],"thanks":[14],"to":[15,70,96,115,134],"their":[16],"strong":[17],"modeling":[18],"capacity":[19],"and":[20,45,50,143,152,167],"large-scale":[21],"pretraining.":[22],"However,":[23],"they":[24],"not":[26],"yet":[27],"conquered":[28],"the":[29,85,98,105,112,117,154],"problem":[30],"of":[31,92,107,119],"image":[32,37,122,160],"matting.":[33,103],"We":[34,147],"hypothesize":[35],"that":[36],"matting":[38,53,79,123,170],"could":[39],"also":[40],"be":[41],"boosted":[42],"by":[43,102,172],"ViTs":[44,72],"present":[46],"a":[47,61,67,173],"new":[48],"efficient":[49],"robust":[51],"ViT-based":[52],"system,":[54],"named":[55],"ViTMatte.":[56],"Our":[57],"method":[58,163],"utilizes":[59],"(i)":[60],"hybrid":[62],"attention":[63],"mechanism":[64],"combined":[65],"with":[66,124],"convolution":[68],"neck":[69],"help":[71],"achieve":[73],"an":[74],"excellent":[75],"performance-computation":[76],"trade-off":[77],"in":[78],"tasks.":[80],"(ii)":[81],"Additionally,":[82],"we":[83],"introduce":[84],"detail":[86],"capture":[87],"module,":[88],"which":[89],"just":[90],"consists":[91],"simple":[93],"lightweight":[94],"convolutions":[95],"complement":[97],"detailed":[99],"information":[100],"required":[101],"To":[104],"best":[106],"our":[108,162],"knowledge,":[109],"ViTMatte":[110,149],"is":[111],"first":[113],"work":[114],"unleash":[116],"potential":[118],"ViT":[120,133],"concise":[125,140],"adaptation.":[126],"It":[127],"inherits":[128],"many":[129],"superior":[130],"properties":[131],"from":[132],"matting,":[135,161],"including":[136],"pretraining":[138],"strategies,":[139],"architecture":[141],"design,":[142],"flexible":[144],"inference":[145],"strategies.":[146],"evaluate":[148],"Composition-1k":[151],"Distinctions-646,":[153],"most":[155],"commonly":[156],"used":[157],"benchmark":[158],"for":[159],"achieves":[164],"state-of-the-art":[165],"outperforms":[168],"prior":[169],"works":[171],"large":[174],"margin.":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}