{"id":"https://openalex.org/W4401633962","doi":"https://doi.org/10.1109/tip.2024.3441813","title":"Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification","display_name":"Multi-Granularity Part Sampling Attention for Fine-Grained Visual Classification","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401633962","doi":"https://doi.org/10.1109/tip.2024.3441813","pmid":"https://pubmed.ncbi.nlm.nih.gov/39150806"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3441813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3441813","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100446916","display_name":"Jiahui Wang","orcid":"https://orcid.org/0000-0002-6438-1506"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-6438-1506","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081006499","display_name":"Qin Xu","orcid":"https://orcid.org/0000-0002-9020-2006"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Xu","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9020-2006","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053609164","display_name":"Bo Jiang","orcid":"https://orcid.org/0000-0002-6238-1596"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Jiang","raw_affiliation_strings":["Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-6238-1596","affiliations":[{"raw_affiliation_string":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372676","display_name":"Bin Luo","orcid":"https://orcid.org/0000-0001-5948-5055"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Luo","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5948-5055","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035112538","display_name":"Jinhui Tang","orcid":"https://orcid.org/0000-0001-9008-222X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Tang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9008-222X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.1382,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.98295232,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"33","issue":null,"first_page":"4529","last_page":"4542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9959999918937683,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9955999851226807,"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/granularity","display_name":"Granularity","score":0.7935447096824646},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7766323685646057},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7765011787414551},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.648077130317688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6361778378486633},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5894001722335815},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5607410669326782},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.43603426218032837},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.42621710896492004},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35168933868408203},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3288882374763489},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2712283134460449},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2585853636264801}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.7935447096824646},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7766323685646057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7765011787414551},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.648077130317688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6361778378486633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5894001722335815},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5607410669326782},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.43603426218032837},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42621710896492004},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35168933868408203},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3288882374763489},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2712283134460449},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2585853636264801},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3441813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3441813","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:39150806","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39150806","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G1048221617","display_name":null,"funder_award_id":"2108085Y23","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G2231845458","display_name":null,"funder_award_id":"61860206004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8523469042","display_name":null,"funder_award_id":"2022i01020014","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327777","display_name":"Jiangsu Provincial Key Research and Development Program","ror":null},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1797268635","https://openalex.org/W1954152232","https://openalex.org/W2104657103","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2737725206","https://openalex.org/W2752782242","https://openalex.org/W2763070548","https://openalex.org/W2765407302","https://openalex.org/W2797977484","https://openalex.org/W2798381792","https://openalex.org/W2899663614","https://openalex.org/W2948437274","https://openalex.org/W2949736877","https://openalex.org/W2951464224","https://openalex.org/W2962858109","https://openalex.org/W2963407932","https://openalex.org/W2965318645","https://openalex.org/W2986821660","https://openalex.org/W2990495699","https://openalex.org/W2992308087","https://openalex.org/W2998345525","https://openalex.org/W2998619563","https://openalex.org/W3000388098","https://openalex.org/W3005359536","https://openalex.org/W3008809756","https://openalex.org/W3108870912","https://openalex.org/W3117668545","https://openalex.org/W3128999341","https://openalex.org/W3133008479","https://openalex.org/W3138516171","https://openalex.org/W3139434170","https://openalex.org/W3172096628","https://openalex.org/W3174336354","https://openalex.org/W3178389175","https://openalex.org/W3194454787","https://openalex.org/W3195399086","https://openalex.org/W3200659198","https://openalex.org/W3205065953","https://openalex.org/W3206734547","https://openalex.org/W3212813052","https://openalex.org/W3213192039","https://openalex.org/W3213639431","https://openalex.org/W4200056912","https://openalex.org/W4206237889","https://openalex.org/W4206378740","https://openalex.org/W4289752563","https://openalex.org/W4312235460","https://openalex.org/W4312359177","https://openalex.org/W4312361652","https://openalex.org/W4312380264","https://openalex.org/W4312823383","https://openalex.org/W4312960790","https://openalex.org/W4313886956","https://openalex.org/W4320008793","https://openalex.org/W4321021073","https://openalex.org/W4323556915","https://openalex.org/W4386065693","https://openalex.org/W4386138397","https://openalex.org/W4386832633","https://openalex.org/W4390278141","https://openalex.org/W4390661786","https://openalex.org/W4390871942","https://openalex.org/W4393154594","https://openalex.org/W6631190155","https://openalex.org/W6638319203","https://openalex.org/W6755977528","https://openalex.org/W6780226713","https://openalex.org/W6798264847","https://openalex.org/W6850824630"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W3112714922","https://openalex.org/W3040691452"],"abstract_inverted_index":{"Fine-grained":[0],"visual":[1,20,85,212],"classification":[2,213],"aims":[3],"to":[4,62,96,118,164,178],"classify":[5],"similar":[6],"sub-categories":[7],"with":[8,110,188],"the":[9,15,32,44,64,98,106,136,141,153,161,166,180,185,189,192,201],"challenges":[10],"of":[11,31,68,101,114,122,155,191],"large":[12],"variations":[13],"within":[14],"same":[16],"sub-category":[17],"and":[18,104,183],"high":[19],"similarities":[21],"between":[22],"different":[23,102,115],"sub-categories.":[24],"Recently,":[25],"methods":[26,42],"that":[27,200],"extract":[28,43,97,119],"semantic":[29,138],"parts":[30,139,157],"discriminative":[33,111],"regions":[34],"have":[35],"attracted":[36],"increasing":[37],"attention.":[38],"However,":[39],"most":[40],"existing":[41],"part":[45,91,99,112,120,130,147,162],"features":[46,113,121,182],"via":[47],"rectangular":[48],"bounding":[49],"boxes":[50],"by":[51],"object":[52],"detection":[53],"module":[54],"or":[55],"attention":[56,149],"mechanism,":[57],"which":[58,133],"makes":[59],"it":[60],"difficult":[61],"capture":[63],"rich":[65],"shape":[66],"information":[67,100],"objects.":[69],"In":[70,169],"this":[71],"paper,":[72],"we":[73,128,171],"propose":[74,129,172],"a":[75,88,173],"novel":[76,89,174],"Multi-Granularity":[77],"Part":[78],"Sampling":[79],"Attention":[80],"(MPSA)":[81],"network":[82],"for":[83],"fine-grained":[84,211],"classification.":[86],"First,":[87],"multi-granularity":[90,175],"retrospect":[92],"block":[93],"is":[94,218],"designed":[95],"scales":[103],"enhance":[105],"high-level":[107],"feature":[108,142],"representation":[109],"granularities.":[116],"Then,":[117],"various":[123],"shapes":[124],"at":[125,221],"each":[126],"granularity,":[127],"sampling":[131,148],"attention,":[132],"can":[134],"sample":[135],"implicit":[137],"on":[140,207],"maps":[143],"comprehensively.":[144],"The":[145,215],"proposed":[146,202],"not":[150],"only":[151],"considers":[152],"importance":[154],"sampled":[156],"but":[158],"also":[159],"adopts":[160],"dropout":[163],"reduce":[165],"overfitting":[167],"issue.":[168],"addition,":[170],"fusion":[176],"method":[177],"highlight":[179],"foreground":[181],"suppress":[184],"background":[186],"noises":[187],"assistance":[190],"gradient":[193],"class":[194],"activation":[195],"map.":[196],"Experimental":[197],"results":[198],"demonstrate":[199],"MPSA":[203],"achieves":[204],"state-of-the-art":[205],"performance":[206],"four":[208],"commonly":[209],"used":[210],"benchmarks.":[214],"source":[216],"code":[217],"publicly":[219],"available":[220],"https://github.com/mobulan/MPSA.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}