{"id":"https://openalex.org/W4402351057","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651230","title":"Enhance Fine-Grained Visual Classification with Attention-Guided Region Selection and Contrastive Feature Alignment","display_name":"Enhance Fine-Grained Visual Classification with Attention-Guided Region Selection and Contrastive Feature Alignment","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351057","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651230"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651230","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5089564180","display_name":"Jin Chen","orcid":"https://orcid.org/0000-0002-6497-4141"},"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":"Jin Chen","raw_affiliation_strings":["Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101924913","display_name":"Huan Wang","orcid":"https://orcid.org/0000-0003-2563-1135"},"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":"Huan Wang","raw_affiliation_strings":["Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"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":"34","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9988999962806702,"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":0.9984999895095825,"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":0.9976000189781189,"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":0.7972079515457153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.631402313709259},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5942741632461548},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.563186764717102},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49844861030578613},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4541565179824829},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42364501953125},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0614871084690094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972079515457153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.631402313709259},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5942741632461548},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.563186764717102},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49844861030578613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4541565179824829},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42364501953125},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0614871084690094},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651230","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W56385144","https://openalex.org/W1797268635","https://openalex.org/W1846799578","https://openalex.org/W1954152232","https://openalex.org/W2138011018","https://openalex.org/W2138621090","https://openalex.org/W2194775991","https://openalex.org/W2202499615","https://openalex.org/W2763070548","https://openalex.org/W2797977484","https://openalex.org/W2889469641","https://openalex.org/W2961018736","https://openalex.org/W2963407932","https://openalex.org/W2964350391","https://openalex.org/W2982512212","https://openalex.org/W2986821660","https://openalex.org/W2998345525","https://openalex.org/W2998619563","https://openalex.org/W3035367622","https://openalex.org/W3101840387","https://openalex.org/W3107331169","https://openalex.org/W3108870912","https://openalex.org/W3138516171","https://openalex.org/W3139434170","https://openalex.org/W3166091781","https://openalex.org/W3172509117","https://openalex.org/W3172752666","https://openalex.org/W3174336354","https://openalex.org/W3178389175","https://openalex.org/W3187646339","https://openalex.org/W3195399086","https://openalex.org/W3200944276","https://openalex.org/W3206734547","https://openalex.org/W3212813052","https://openalex.org/W3213792864","https://openalex.org/W4288622677","https://openalex.org/W4293197791","https://openalex.org/W4304084267","https://openalex.org/W4308737504","https://openalex.org/W4312235460","https://openalex.org/W4312361652","https://openalex.org/W4312823383","https://openalex.org/W4313886956","https://openalex.org/W4321021073","https://openalex.org/W4328101918","https://openalex.org/W4385245566","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6803650990"],"related_works":["https://openalex.org/W4386564352","https://openalex.org/W2952668426","https://openalex.org/W4386159726","https://openalex.org/W2601157893","https://openalex.org/W2131735617","https://openalex.org/W2373006798","https://openalex.org/W2056912418","https://openalex.org/W2123759770","https://openalex.org/W2033213769","https://openalex.org/W4312376745"],"abstract_inverted_index":{"Vision":[0],"Transformers":[1],"(ViTs)":[2],"have":[3],"shown":[4],"great":[5],"potential":[6],"in":[7,25],"Fine-grained":[8],"Visual":[9],"Classification":[10],"(FGVC).":[11],"In":[12],"FGVC":[13,211],"task,":[14],"higher":[15],"input":[16,54],"resolution":[17],"is":[18],"commonly":[19],"employed":[20],"to":[21,38,47,159],"assist":[22],"the":[23,34,44,53,103,132,138,144,148,161,178,197,204,207],"model":[24],"capturing":[26],"detailed":[27,49],"feature":[28,193],"representations.":[29,194],"However,":[30],"for":[31,122,190],"ViTs,":[32],"augmenting":[33],"image":[35],"size":[36],"leads":[37],"significant":[39],"computational":[40],"overhead.":[41],"To":[42],"improve":[43],"model\u2019s":[45],"ability":[46],"extract":[48],"features":[50,162,168],"without":[51],"altering":[52],"size,":[55],"we":[56,175],"introduce":[57],"a":[58],"method":[59,179],"called":[60],"Attention-guided":[61],"Region":[62,80],"Selection":[63,81],"and":[64,83,96,106,169],"Contrastive":[65,84],"Feature":[66,85],"Alignment":[67,86],"(ARS-CFA).":[68],"ARS-CFA":[69],"consists":[70],"of":[71,140,150,163,180,199,206],"three":[72],"primary":[73],"modules:":[74],"Attention":[75],"Score":[76],"Aggregation":[77],"(ASA),":[78],"Focal":[79],"(FRS),":[82],"(CFA).":[87],"The":[88,109,153],"ASA":[89],"module":[90,111,155],"extracts":[91],"attention":[92],"weights":[93],"between":[94,102],"patches":[95],"aggregates":[97],"them":[98],"into":[99,124],"relevance":[100,117],"scores":[101],"class":[104],"token":[105],"other":[107],"tokens.":[108],"FRS":[110],"selects":[112],"discriminative":[113,167],"regions":[114],"based":[115],"on":[116,209],"scores,":[118],"obtaining":[119],"finer-scale":[120],"images":[121],"reinsertion":[123],"training.":[125],"These":[126],"fine-scale":[127],"images,":[128,134,165],"when":[129],"paired":[130,164],"with":[131,183,203],"original":[133],"can":[135],"also":[136],"address":[137],"lack":[139],"similar":[141],"samples":[142],"within":[143],"same":[145],"batch,":[146],"enhancing":[147,187],"efficacy":[149],"contrastive":[151,157,184],"loss.":[152],"CFA":[154],"adopts":[156],"loss":[158],"align":[160],"mining":[166],"suppressing":[170],"noise.":[171],"With":[172],"these":[173],"modules,":[174],"aptly":[176],"combine":[177],"region":[181],"selection":[182],"loss,":[185],"significantly":[186],"ViT\u2019s":[188],"capacity":[189],"extracting":[191],"fine-grained":[192],"Experiments":[195],"demonstrate":[196],"effectiveness":[198],"our":[200],"approach":[201],"compared":[202],"state":[205],"art":[208],"six":[210],"benchmarks.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}