{"id":"https://openalex.org/W4361790919","doi":"https://doi.org/10.1145/3577530.3577586","title":"Attention-based Multi-scale ViT Fine-grained Visual Classification","display_name":"Attention-based Multi-scale ViT Fine-grained Visual Classification","publication_year":2022,"publication_date":"2022-12-09","ids":{"openalex":"https://openalex.org/W4361790919","doi":"https://doi.org/10.1145/3577530.3577586"},"language":"en","primary_location":{"id":"doi:10.1145/3577530.3577586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577530.3577586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5088130618","display_name":"Rujia Li","orcid":"https://orcid.org/0000-0001-8009-530X"},"institutions":[{"id":"https://openalex.org/I41317344","display_name":"Jiangxi Science and Technology Normal University","ror":"https://ror.org/04r1zkp10","country_code":"CN","type":"education","lineage":["https://openalex.org/I41317344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rujia Li","raw_affiliation_strings":["Graduate School, Jiangxi Science and Technology Normal University, China"],"raw_orcid":"https://orcid.org/0000-0001-8009-530X","affiliations":[{"raw_affiliation_string":"Graduate School, Jiangxi Science and Technology Normal University, China","institution_ids":["https://openalex.org/I41317344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025360329","display_name":"Junya Liu","orcid":"https://orcid.org/0000-0002-6957-8607"},"institutions":[{"id":"https://openalex.org/I41317344","display_name":"Jiangxi Science and Technology Normal University","ror":"https://ror.org/04r1zkp10","country_code":"CN","type":"education","lineage":["https://openalex.org/I41317344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junya Liu","raw_affiliation_strings":["Foreign Languages College, Jiangxi Science and Technology Normal University, China"],"raw_orcid":"https://orcid.org/0000-0002-6957-8607","affiliations":[{"raw_affiliation_string":"Foreign Languages College, Jiangxi Science and Technology Normal University, China","institution_ids":["https://openalex.org/I41317344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031803321","display_name":"Zhen Yang","orcid":"https://orcid.org/0000-0002-0785-9382"},"institutions":[{"id":"https://openalex.org/I41317344","display_name":"Jiangxi Science and Technology Normal University","ror":"https://ror.org/04r1zkp10","country_code":"CN","type":"education","lineage":["https://openalex.org/I41317344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Yang","raw_affiliation_strings":["Graduate School, Jiangxi Science and Technology Normal University, China"],"raw_orcid":"https://orcid.org/0000-0002-0785-9382","affiliations":[{"raw_affiliation_string":"Graduate School, Jiangxi Science and Technology Normal University, China","institution_ids":["https://openalex.org/I41317344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007633349","display_name":"Xin Zhou","orcid":"https://orcid.org/0000-0001-5405-9890"},"institutions":[{"id":"https://openalex.org/I41317344","display_name":"Jiangxi Science and Technology Normal University","ror":"https://ror.org/04r1zkp10","country_code":"CN","type":"education","lineage":["https://openalex.org/I41317344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhou","raw_affiliation_strings":["Graduate School, Jiangxi Science and Technology Normal University, China"],"raw_orcid":"https://orcid.org/0000-0001-5405-9890","affiliations":[{"raw_affiliation_string":"Graduate School, Jiangxi Science and Technology Normal University, China","institution_ids":["https://openalex.org/I41317344"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044306288","display_name":"Zhijian Yin","orcid":"https://orcid.org/0000-0001-5683-802X"},"institutions":[{"id":"https://openalex.org/I41317344","display_name":"Jiangxi Science and Technology Normal University","ror":"https://ror.org/04r1zkp10","country_code":"CN","type":"education","lineage":["https://openalex.org/I41317344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Yin","raw_affiliation_strings":["Graduate School, Jiangxi Science and Technology Normal University, China"],"raw_orcid":"https://orcid.org/0000-0001-5683-802X","affiliations":[{"raw_affiliation_string":"Graduate School, Jiangxi Science and Technology Normal University, China","institution_ids":["https://openalex.org/I41317344"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41317344"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T10036","display_name":"Advanced Neural Network Applications","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/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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.7846096158027649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7220512628555298},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.701339840888977},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6339336037635803},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5487053394317627},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5477492213249207},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5379872918128967},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5013003349304199},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4938248097896576},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4293195605278015},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4088379144668579},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16083812713623047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7846096158027649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7220512628555298},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.701339840888977},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6339336037635803},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5487053394317627},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5477492213249207},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5379872918128967},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5013003349304199},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4938248097896576},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4293195605278015},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4088379144668579},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16083812713623047},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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":1,"locations":[{"id":"doi:10.1145/3577530.3577586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577530.3577586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 6th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.550000011920929,"id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G1437769313","display_name":null,"funder_award_id":"62061019","funder_id":"https://openalex.org/F4320334062","funder_display_name":"National Natural Science Foundation of China-Liaoning Joint Fund"}],"funders":[{"id":"https://openalex.org/F4320334062","display_name":"National Natural Science Foundation of China-Liaoning Joint Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2117287331","https://openalex.org/W2138011018","https://openalex.org/W2194775991","https://openalex.org/W2460852148","https://openalex.org/W2966316879","https://openalex.org/W2998345525","https://openalex.org/W3096609285","https://openalex.org/W3124951096","https://openalex.org/W4236965008","https://openalex.org/W4362597616"],"related_works":["https://openalex.org/W2022849497","https://openalex.org/W3081299480","https://openalex.org/W2407190427","https://openalex.org/W2919210741","https://openalex.org/W2907584218","https://openalex.org/W3002446410","https://openalex.org/W4390224712","https://openalex.org/W2797752778","https://openalex.org/W4322096758","https://openalex.org/W3197089899"],"abstract_inverted_index":{"Fine-grained":[0,142],"visual":[1,47],"classification":[2,10,153],"(FGVC)":[3],"is":[4,108],"a":[5,91],"challenging":[6],"task":[7],"in":[8,62,77,147],"image":[9,63],"due":[11],"to":[12,58,82,110,124,133],"the":[13,19,25,52,73,84,95,127,130],"small":[14],"differences":[15,21],"between":[16],"classes":[17],"and":[18,37,67,89,102,116],"large":[20],"within":[22],"subclasses.":[23],"In":[24,49],"early":[26],"works,":[27],"some":[28],"methods":[29,44],"mainly":[30],"rely":[31],"on":[32,42,155],"constructing":[33],"bounding":[34],"box":[35],"annotations":[36],"integrating":[38],"attention":[39,105],"mechanisms":[40],"based":[41],"CNN":[43,85],"for":[45],"fine-grained":[46,157],"classification.":[48],"recent":[50],"years,":[51],"Vision":[53],"Transformer":[54],"(ViT)":[55],"has":[56,150],"begun":[57],"show":[59],"better":[60],"performance":[61,74],"classification,":[64],"object":[65,68],"detection,":[66],"tracking.":[69],"To":[70],"further":[71,125],"investigate":[72],"of":[75,129],"ViT":[76,88,141],"FGVC,":[78],"this":[79,148],"paper":[80],"proposes":[81],"combine":[83],"method":[86],"with":[87],"introduce":[90],"dual-path":[92],"hierarchy":[93],"into":[94],"pyramid":[96],"structure":[97],"-":[98],"top-down":[99],"feature":[100,135],"path":[101],"bottom-up":[103],"channel-spatial":[104],"path;":[106],"DropBlock":[107],"used":[109,123],"accurately":[111],"localize":[112],"discriminative":[113],"regions;":[114],"SENet":[115],"global":[117],"covariance":[118],"pooling":[119],"(GCP)":[120],"measures":[121],"are":[122],"enhance":[126],"ability":[128],"network":[131],"model":[132],"extract":[134],"maps":[136],"information.":[137],"The":[138],"Attention-based":[139],"Multi-scale":[140],"Visual":[143],"Classification":[144],"(AMViT-CNN)":[145],"proposed":[146],"work":[149],"achieved":[151],"good":[152],"results":[154],"public":[156],"datasets":[158],"(CUB-200-2011,":[159],"Stanford-Cars).":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}