{"id":"https://openalex.org/W4323240248","doi":"https://doi.org/10.5220/0011611100003417","title":"Salient Mask-Guided Vision Transformer for Fine-Grained Classification","display_name":"Salient Mask-Guided Vision Transformer for Fine-Grained Classification","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323240248","doi":"https://doi.org/10.5220/0011611100003417"},"language":"en","primary_location":{"id":"doi:10.5220/0011611100003417","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011611100003417","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 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0011611100003417","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063606702","display_name":"Dmitry Demidov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Dmitry Demidov","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, U.A.E., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, U.A.E., --- Select a Country ---","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010593762","display_name":"M. Sharif","orcid":"https://orcid.org/0000-0001-6845-3506"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Muhammad Sharif","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, U.A.E., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, U.A.E., --- Select a Country ---","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043376474","display_name":"Aliakbar Abdurahimov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Aliakbar Abdurahimov","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, U.A.E., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, U.A.E., --- Select a Country ---","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009362997","display_name":"Hisham Cholakkal","orcid":"https://orcid.org/0000-0002-8230-9065"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Hisham Cholakkal","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, U.A.E., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, U.A.E., --- Select a Country ---","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fahad Khan","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, U.A.E., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, U.A.E., --- Select a Country ---","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7964,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87048691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"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/discriminative-model","display_name":"Discriminative model","score":0.9030516147613525},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7642045617103577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7412661910057068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6928737759590149},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5762797594070435},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4599129557609558},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42820116877555847},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3236194849014282}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9030516147613525},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7642045617103577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412661910057068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6928737759590149},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5762797594070435},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4599129557609558},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42820116877555847},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3236194849014282},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0011611100003417","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011611100003417","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 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.07102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.07102","pdf_url":"https://arxiv.org/pdf/2305.07102","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.5220/0011611100003417","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0011611100003417","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 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1846799578","https://openalex.org/W1928906481","https://openalex.org/W1977914407","https://openalex.org/W1980526845","https://openalex.org/W2108598243","https://openalex.org/W2118696714","https://openalex.org/W2134670479","https://openalex.org/W2138011018","https://openalex.org/W2142697503","https://openalex.org/W2159423002","https://openalex.org/W2194775991","https://openalex.org/W2202499615","https://openalex.org/W2533598788","https://openalex.org/W2604134068","https://openalex.org/W2740667773","https://openalex.org/W2781067279","https://openalex.org/W2797977484","https://openalex.org/W2798365843","https://openalex.org/W2798775284","https://openalex.org/W2883502031","https://openalex.org/W2896457183","https://openalex.org/W2963393555","https://openalex.org/W2963407932","https://openalex.org/W2963563276","https://openalex.org/W2963631907","https://openalex.org/W2964051877","https://openalex.org/W2964110616","https://openalex.org/W2986456235","https://openalex.org/W2986821660","https://openalex.org/W2990495699","https://openalex.org/W2997426000","https://openalex.org/W3025800305","https://openalex.org/W3035220232","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3108333276","https://openalex.org/W3108815824","https://openalex.org/W3115390238","https://openalex.org/W3124951096","https://openalex.org/W3126080715","https://openalex.org/W3127751679","https://openalex.org/W3128449120","https://openalex.org/W3129197028","https://openalex.org/W3130788242","https://openalex.org/W3138516171","https://openalex.org/W3139434170","https://openalex.org/W3170841864","https://openalex.org/W3170874841","https://openalex.org/W3171930565","https://openalex.org/W3178389175","https://openalex.org/W3182672186","https://openalex.org/W3190140211","https://openalex.org/W3203876692","https://openalex.org/W4221154675","https://openalex.org/W4226530256","https://openalex.org/W4281483658","https://openalex.org/W4283728882","https://openalex.org/W4287330514","https://openalex.org/W4287572671","https://openalex.org/W4303633479","https://openalex.org/W4304084267","https://openalex.org/W4312361652","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2082783427"],"abstract_inverted_index":{"Fine-grained":[0],"visual":[1],"classification":[2,92],"(FGVC)":[3],"is":[4,13,26,159],"a":[5,141],"challenging":[6],"computer":[7],"vision":[8],"problem,":[9],"where":[10,150],"the":[11,28,52,66,85,91,105,109,116,151,154,174],"task":[12],"to":[14,59,73,81,104,114],"automatically":[15],"recognise":[16],"objects":[17],"from":[18,98],"subordinate":[19],"categories.":[20],"One":[21],"of":[22,108,153,164],"its":[23],"main":[24],"difficulties":[25],"capturing":[27],"most":[29,117],"discriminative":[30,62,78,166],"inter-class":[31,119],"variances":[32],"among":[33,187],"visually":[34],"similar":[35],"classes.":[36],"Recently,":[37],"methods":[38],"with":[39,55,173],"Vision":[40,147],"Transformer":[41,148],"(ViT)":[42],"have":[43],"demonstrated":[44],"noticeable":[45],"achievements":[46],"in":[47,90],"FGVC,":[48],"generally":[49],"by":[50],"employing":[51],"self-attention":[53,87],"mechanism":[54],"additional":[56],"resource-consuming":[57],"techniques":[58],"distinguish":[60],"potentially":[61,165],"regions":[63,79,128],"while":[64,191],"disregarding":[65],"rest.":[67],"However,":[68],"such":[69],"approaches":[70,190],"may":[71,112,129],"struggle":[72],"effectively":[74],"focus":[75],"on":[76,84,183],"truly":[77],"due":[80,103],"only":[82],"relying":[83],"inherent":[86],"mechanism,":[88],"resulting":[89],"token":[93],"likely":[94],"aggregating":[95],"global":[96],"information":[97],"less-important":[99],"background":[100,127],"patches.":[101],"Moreover,":[102],"immense":[106],"lack":[107],"datapoints,":[110],"classifiers":[111],"fail":[113],"find":[115],"helpful":[118],"distinguishing":[120],"features,":[121],"since":[122],"other":[123],"unrelated":[124],"but":[125],"distinctive":[126],"be":[130],"falsely":[131],"recognised":[132],"as":[133],"being":[134],"valuable.":[135],"To":[136],"this":[137],"end,":[138],"we":[139],"introduce":[140],"simple":[142],"yet":[143],"effective":[144],"Salient":[145],"Mask-Guided":[146],"(SM-ViT),":[149],"discriminability":[152],"standard":[155,175],"ViT`s":[156],"attention":[157],"maps":[158],"boosted":[160],"through":[161],"salient":[162],"masking":[163],"foreground":[167],"regions.":[168],"Extensive":[169],"experiments":[170],"demonstrate":[171],"that":[172],"training":[176],"procedure":[177],"our":[178],"SM-ViT":[179],"achieves":[180],"state-of-the-art":[181],"performance":[182],"popular":[184],"FGVC":[185],"benchmarks":[186],"existing":[188],"ViT-based":[189],"requiring":[192],"fewer":[193],"resources":[194],"and":[195],"lower":[196],"input":[197],"image":[198],"resolution.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
