{"id":"https://openalex.org/W7125911834","doi":"https://doi.org/10.1109/smc58881.2025.11343602","title":"Few-Shot Fine-Grained Image Classification via Vision Transformer","display_name":"Few-Shot Fine-Grained Image Classification via Vision Transformer","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125911834","doi":"https://doi.org/10.1109/smc58881.2025.11343602"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124141012","display_name":"Yongqi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongqi Liu","raw_affiliation_strings":["Chongqing University,College of Computer Science,Chongqing,China,400044"],"affiliations":[{"raw_affiliation_string":"Chongqing University,College of Computer Science,Chongqing,China,400044","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015300690","display_name":"Tong Xiao","orcid":"https://orcid.org/0009-0007-7082-6085"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xiao","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124103054","display_name":"Zeao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeao Chen","raw_affiliation_strings":["Chongqing University,College of Computer Science,Chongqing,China,400044"],"affiliations":[{"raw_affiliation_string":"Chongqing University,College of Computer Science,Chongqing,China,400044","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105513298","display_name":"Chen Zhou","orcid":"https://orcid.org/0000-0003-1209-2590"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhou","raw_affiliation_strings":["Chongqing University,College of Computer Science,Chongqing,China,400044"],"affiliations":[{"raw_affiliation_string":"Chongqing University,College of Computer Science,Chongqing,China,400044","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115695232","display_name":"Zhijie Wang","orcid":"https://orcid.org/0000-0002-6266-772X"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi-Jie Wang","raw_affiliation_strings":["Chongqing University,College of Computer Science,Chongqing,China,400044"],"affiliations":[{"raw_affiliation_string":"Chongqing University,College of Computer Science,Chongqing,China,400044","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5124141012"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72690507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1550","last_page":"1555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2678999900817871,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2678999900817871,"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":0.14300000667572021,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.09149999916553497,"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/encoder","display_name":"Encoder","score":0.5534999966621399},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5436000227928162},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5353000164031982},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4794999957084656},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45249998569488525},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44269999861717224},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4106999933719635},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3709000051021576}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7146000266075134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6069999933242798},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5534999966621399},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5436000227928162},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5080999732017517},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4794999957084656},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45249998569488525},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.36640000343322754},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.33219999074935913},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.26649999618530273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1955942245","https://openalex.org/W2104657103","https://openalex.org/W2591924527","https://openalex.org/W2898895571","https://openalex.org/W2951464224","https://openalex.org/W2964193299","https://openalex.org/W2998345525","https://openalex.org/W3025800305","https://openalex.org/W3035220232","https://openalex.org/W3107763055","https://openalex.org/W3139434170","https://openalex.org/W3206402863","https://openalex.org/W3216686652","https://openalex.org/W4214612132","https://openalex.org/W4312359569","https://openalex.org/W4312446817","https://openalex.org/W4316660800","https://openalex.org/W4319163914","https://openalex.org/W4382462216","https://openalex.org/W4389060294","https://openalex.org/W4390871781","https://openalex.org/W4393148571","https://openalex.org/W4394015587","https://openalex.org/W4399039831","https://openalex.org/W4400216981","https://openalex.org/W4402191334","https://openalex.org/W4403780736"],"related_works":[],"abstract_inverted_index":{"Few-shot":[0],"fine-grained":[1,14],"image":[2,101,128],"classification":[3],"(FS-FGIC)":[4],"is":[5,163],"to":[6,71,104,123,141],"classify":[7],"images":[8],"of":[9,22,39,108,114,145],"the":[10,42,51,87,106,111,143,160],"same":[11],"class":[12],"into":[13,137],"subclasses,":[15],"where":[16],"only":[17],"a":[18,91,119],"very":[19],"limited":[20],"number":[21,144],"labeled":[23,35],"samples":[24],"in":[25,62],"each":[26,138],"subclass":[27],"are":[28,46],"available":[29],"(e.g.,":[30],"5":[31],"or":[32,77],"even":[33],"1":[34],"sample).":[36],"For":[37],"most":[38],"existing":[40],"methods,":[41],"feature":[43,59],"representation":[44,60],"capabilities":[45,61],"insufficient,":[47],"which":[48],"may":[49],"harm":[50],"performance.":[52],"Vision":[53],"Transformers":[54],"(ViTs)":[55],"have":[56],"shown":[57],"strong":[58],"many":[63],"research":[64],"fields.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,81,98,117,132],"attempt":[70],"solve":[72],"FSFGIC":[73],"problem":[74],"via":[75],"ViT":[76,85,109],"its":[78],"variants.":[79],"Generally,":[80],"use":[82],"an":[83,100,134],"enhanced":[84],"as":[86],"backbone":[88],"and":[89,130],"adopt":[90],"three-stage":[92],"training":[93],"strategy.":[94],"More":[95],"specifically,":[96],"(i)":[97],"utilize":[99],"matting":[102],"module":[103,122,136],"enhance":[105],"focus":[107,125],"on":[110,126,153],"main":[112],"subjects":[113],"images;":[115],"(ii)":[116],"introduce":[118],"part":[120],"selection":[121],"better":[124],"local":[127],"details;":[129],"(iii)":[131],"incorporate":[133],"AdaptMLP":[135],"Transformer":[139],"Encoder":[140],"reduce":[142],"parameters":[146],"that":[147,159],"require":[148],"fine-tuning.":[149],"Extensive":[150],"experiments":[151],"based":[152],"three":[154],"benchmark":[155],"datasets":[156],"show":[157],"us":[158],"proposed":[161],"model":[162],"highly":[164],"competitive,":[165],"compared":[166],"against":[167],"state-of-the-art":[168],"models.":[169]},"counts_by_year":[],"updated_date":"2026-02-23T20:09:44.859080","created_date":"2026-01-29T00:00:00"}