{"id":"https://openalex.org/W3204826552","doi":"https://doi.org/10.1109/icassp43922.2022.9747591","title":"A free lunch from ViT: adaptive attention multi-scale fusion Transformer for fine-grained visual recognition","display_name":"A free lunch from ViT: adaptive attention multi-scale fusion Transformer for fine-grained visual recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3204826552","doi":"https://doi.org/10.1109/icassp43922.2022.9747591","mag":"3204826552"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747591","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"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/A5100368775","display_name":"Yuan Zhang","orcid":"https://orcid.org/0009-0000-8003-0725"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,China","School of Software and Microelectronics, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602897","display_name":"Jian Cao","orcid":"https://orcid.org/0000-0001-8903-2903"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cao","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,China","School of Software and Microelectronics, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038765418","display_name":"Ling Zhang","orcid":"https://orcid.org/0000-0001-8371-5252"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Zhang","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,China","School of Software and Microelectronics, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046198377","display_name":"Xiangcheng Liu","orcid":"https://orcid.org/0000-0003-4966-7394"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangcheng Liu","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,China","School of Software and Microelectronics, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645271","display_name":"Zhiyi Wang","orcid":"https://orcid.org/0000-0002-5619-2238"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyi Wang","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,China","School of Software and Microelectronics, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012444471","display_name":"Feng Ling","orcid":"https://orcid.org/0000-0002-0685-4897"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Ling","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,China","School of Software and Microelectronics, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103120794","display_name":"Weiqian Chen","orcid":"https://orcid.org/0000-0002-9232-9027"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqian Chen","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,China","School of Software and Microelectronics, Peking University, China","Alibaba Group, Inc"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Alibaba Group, Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100368775"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":3.8774,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.95258376,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3234","last_page":"3238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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":0.8199498057365417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6139618754386902},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5552941560745239},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5168398022651672},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.501593828201294},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4501219093799591},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43160828948020935},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39047470688819885},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08327829837799072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199498057365417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6139618754386902},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5552941560745239},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5168398022651672},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.501593828201294},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4501219093799591},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43160828948020935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39047470688819885},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08327829837799072},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747591","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1616462885","https://openalex.org/W1797268635","https://openalex.org/W1928906481","https://openalex.org/W2194775991","https://openalex.org/W2202499615","https://openalex.org/W2403585668","https://openalex.org/W2737725206","https://openalex.org/W2740620254","https://openalex.org/W2797977484","https://openalex.org/W2798365843","https://openalex.org/W2889469641","https://openalex.org/W2892035828","https://openalex.org/W2951852399","https://openalex.org/W2963090248","https://openalex.org/W2963393555","https://openalex.org/W2963407932","https://openalex.org/W2964350391","https://openalex.org/W2970507129","https://openalex.org/W2986456235","https://openalex.org/W2986821660","https://openalex.org/W2990495699","https://openalex.org/W2998345525","https://openalex.org/W2998619563","https://openalex.org/W3030520226","https://openalex.org/W3034676907","https://openalex.org/W3081907075","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3108870912","https://openalex.org/W3126558081","https://openalex.org/W3139434170","https://openalex.org/W3206734547","https://openalex.org/W6636475194","https://openalex.org/W6638319203","https://openalex.org/W6640376812","https://openalex.org/W6713467259","https://openalex.org/W6755069125","https://openalex.org/W6767612737","https://openalex.org/W6780770743","https://openalex.org/W6784333009","https://openalex.org/W6792309431"],"related_works":["https://openalex.org/W4287775347","https://openalex.org/W3029282628","https://openalex.org/W3037162118","https://openalex.org/W3116268265","https://openalex.org/W3177367299","https://openalex.org/W2969574947","https://openalex.org/W4285666859","https://openalex.org/W3203212172","https://openalex.org/W4288086191","https://openalex.org/W2972312591"],"abstract_inverted_index":{"Learning":[0],"subtle":[1],"representation":[2],"about":[3],"object":[4],"parts":[5],"plays":[6],"a":[7,75],"vital":[8],"role":[9],"in":[10,38,43,71,91,97],"fine-grained":[11,144],"visual":[12],"recognition":[13],"(FGVR)":[14],"field.":[15],"The":[16,85,112],"vision":[17,25],"transformer":[18],"(ViT)":[19],"achieves":[20],"promising":[21],"results":[22],"on":[23,47,141],"computer":[24],"due":[26],"to":[27,103],"its":[28],"attention":[29,62,80,95],"mechanism.":[30],"Nonetheless,":[31],"with":[32,105],"the":[33,40,48,106],"fixed":[34],"size":[35],"of":[36,109],"patches":[37],"ViT,":[39],"class":[41],"token":[42],"deep":[44],"layer":[45],"focuses":[46],"global":[49],"receptive":[50],"field":[51],"and":[52,66,99,116,126,149],"cannot":[53],"generate":[54],"multi-granularity":[55],"features":[56],"for":[57,68],"FGVR.":[58],"To":[59],"capture":[60],"region":[61],"without":[63],"box":[64],"annotations":[65],"compensate":[67],"ViT":[69,98],"shortcomings":[70],"FGVR,":[72],"we":[73],"propose":[74],"novel":[76],"method":[77],"named":[78],"Adaptive":[79],"multi-scale":[81],"Fusion":[82],"Transformer":[83],"(AFTrans).":[84],"Selective":[86],"Attention":[87],"Collection":[88],"Module":[89],"(SACM)":[90],"our":[92,122],"approach":[93],"leverages":[94],"weights":[96,123],"filters":[100],"them":[101],"adaptively":[102],"correspond":[104],"relative":[107],"importance":[108],"input":[110],"patches.":[111],"multiple":[113],"scales":[114],"(global":[115],"local)":[117],"pipeline":[118],"is":[119],"supervised":[120],"by":[121],"sharing":[124],"encoder":[125],"can":[127,137],"be":[128],"easily":[129],"trained":[130],"end-to-end.":[131],"Comprehensive":[132],"experiments":[133],"demonstrate":[134],"that":[135],"AFTrans":[136],"achieve":[138],"SOTA":[139],"performance":[140],"three":[142],"published":[143],"benchmarks:":[145],"CUB-200-2011,":[146],"Stanford":[147],"Dogs":[148],"iNat2017.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
