{"id":"https://openalex.org/W7169575576","doi":"https://doi.org/10.1016/j.imavis.2026.106119","title":"DistillCvT: Self-supervised distillation of Convolutional Vision Transformers for few-shot fine-grained classification","display_name":"DistillCvT: Self-supervised distillation of Convolutional Vision Transformers for few-shot fine-grained classification","publication_year":2026,"publication_date":"2026-07-17","ids":{"openalex":"https://openalex.org/W7169575576","doi":"https://doi.org/10.1016/j.imavis.2026.106119"},"language":"en","primary_location":{"id":"doi:10.1016/j.imavis.2026.106119","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.imavis.2026.106119","pdf_url":null,"source":{"id":"https://openalex.org/S177430994","display_name":"Image and Vision Computing","issn_l":"0262-8856","issn":["0262-8856","1872-8138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Image and Vision Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.imavis.2026.106119","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084572131","display_name":"Jia Min Lim","orcid":"https://orcid.org/0009-0002-5459-1101"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]},{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Jia Min Lim","raw_affiliation_strings":["Faculty of Information Science and Technology, Multimedia University, Jalan Ayer Keroh Lama, Bukit Beruang, 75450, Melaka, Malaysia","School of Information Technology, Monash University, Jalan Lagoon Selatan, Bandar Sunway, 47500, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0009-0002-5459-1101","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Multimedia University, Jalan Ayer Keroh Lama, Bukit Beruang, 75450, Melaka, Malaysia","institution_ids":["https://openalex.org/I173029219"]},{"raw_affiliation_string":"School of Information Technology, Monash University, Jalan Lagoon Selatan, Bandar Sunway, 47500, Selangor, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017532046","display_name":"Kian Ming Lim","orcid":"https://orcid.org/0000-0003-1929-7978"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]},{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN","MY"],"is_corresponding":true,"raw_author_name":"Kian Ming Lim","raw_affiliation_strings":["School of Computer Science, University of Nottingham, Ningbo, 315100, Zhejiang Province, China","School of Information Technology, Monash University, Jalan Lagoon Selatan, Bandar Sunway, 47500, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-1929-7978","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham, Ningbo, 315100, Zhejiang Province, China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"School of Information Technology, Monash University, Jalan Lagoon Selatan, Bandar Sunway, 47500, Selangor, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008658846","display_name":"Jit Yan Lim","orcid":"https://orcid.org/0000-0003-1704-9460"},"institutions":[{"id":"https://openalex.org/I11662577","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324","country_code":"MY","type":"education","lineage":["https://openalex.org/I11662577"]},{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Jit Yan Lim","raw_affiliation_strings":["Faculty of Information Science and Technology, Multimedia University, Jalan Ayer Keroh Lama, Bukit Beruang, 75450, Melaka, Malaysia","School of Information Technology, Monash University, Jalan Lagoon Selatan, Bandar Sunway, 47500, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-1704-9460","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Multimedia University, Jalan Ayer Keroh Lama, Bukit Beruang, 75450, Melaka, Malaysia","institution_ids":["https://openalex.org/I173029219"]},{"raw_affiliation_string":"School of Information Technology, Monash University, Jalan Lagoon Selatan, Bandar Sunway, 47500, Selangor, Malaysia","institution_ids":["https://openalex.org/I11662577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086127398","display_name":"Chin Poo Lee","orcid":"https://orcid.org/0000-0003-3679-8977"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chin Poo Lee","raw_affiliation_strings":["School of Computer Science, University of Nottingham, Ningbo, 315100, Zhejiang Province, China"],"raw_orcid":"https://orcid.org/0000-0003-3679-8977","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Nottingham, Ningbo, 315100, Zhejiang Province, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015350300","display_name":"Pey Yun Goh","orcid":"https://orcid.org/0000-0003-2060-3223"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Pey Yun Goh","raw_affiliation_strings":["Faculty of Information Science and Technology, Multimedia University, Jalan Ayer Keroh Lama, Bukit Beruang, 75450, Melaka, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-2060-3223","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Multimedia University, Jalan Ayer Keroh Lama, Bukit Beruang, 75450, Melaka, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008658846","https://openalex.org/A5017532046","https://openalex.org/A5084572131"],"corresponding_institution_ids":["https://openalex.org/I11662577","https://openalex.org/I13591777","https://openalex.org/I173029219"],"apc_list":{"value":2100,"currency":"USD","value_usd":2100},"apc_paid":{"value":2100,"currency":"USD","value_usd":2100},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74137122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"174","issue":null,"first_page":"106119","last_page":"106119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.2994999885559082,"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":0.2994999885559082,"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":0.15230000019073486,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.03620000183582306,"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/transformer","display_name":"Transformer","score":0.6304000020027161},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5074999928474426},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5033000111579895},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.4767000079154968},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.2646999955177307}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6899999976158142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6858000159263611},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6304000020027161},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.567300021648407},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5074999928474426},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.241799995303154},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.24040000140666962}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.imavis.2026.106119","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.imavis.2026.106119","pdf_url":null,"source":{"id":"https://openalex.org/S177430994","display_name":"Image and Vision Computing","issn_l":"0262-8856","issn":["0262-8856","1872-8138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Image and Vision Computing","raw_type":"journal-article"},{"id":"pmh:oai:shdl.mmu.edu.my:16464","is_oa":false,"landing_page_url":"https://shdl.mmu.edu.my/16464/1/1-s2.0-S026288562600226X-main.pdf","pdf_url":"https://shdl.mmu.edu.my/16464/1/1-s2.0-S026288562600226X-main.pdf","source":{"id":"https://openalex.org/S4377196753","display_name":"Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173029219","host_organization_name":"Multimedia University","host_organization_lineage":["https://openalex.org/I173029219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1016/j.imavis.2026.106119","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.imavis.2026.106119","pdf_url":null,"source":{"id":"https://openalex.org/S177430994","display_name":"Image and Vision Computing","issn_l":"0262-8856","issn":["0262-8856","1872-8138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Image and Vision Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5185539722442627,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G821617575","display_name":null,"funder_award_id":"I-M010-SED-000416","funder_id":"https://openalex.org/F4320326583","funder_display_name":"Monash University Malaysia"}],"funders":[{"id":"https://openalex.org/F4320326583","display_name":"Monash University Malaysia","ror":"https://ror.org/00yncr324"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2138011018","https://openalex.org/W2957105406","https://openalex.org/W2964060161","https://openalex.org/W2964105864","https://openalex.org/W2965572487","https://openalex.org/W2979689312","https://openalex.org/W3019704403","https://openalex.org/W3034978645","https://openalex.org/W3035607448","https://openalex.org/W3092900959","https://openalex.org/W3107763055","https://openalex.org/W3116954826","https://openalex.org/W3126133447","https://openalex.org/W3176341011","https://openalex.org/W4214493665","https://openalex.org/W4220752330","https://openalex.org/W4280538209","https://openalex.org/W4283834642","https://openalex.org/W4290790999","https://openalex.org/W4295760561","https://openalex.org/W4296984528","https://openalex.org/W4303982493","https://openalex.org/W4304098587","https://openalex.org/W4312500832","https://openalex.org/W4316660800","https://openalex.org/W4319299899","https://openalex.org/W4353056557","https://openalex.org/W4388615943","https://openalex.org/W4389158478","https://openalex.org/W4391795396","https://openalex.org/W4394015587","https://openalex.org/W4399800996","https://openalex.org/W4404238284","https://openalex.org/W4406616246","https://openalex.org/W4408326908","https://openalex.org/W4408977863","https://openalex.org/W4410014420","https://openalex.org/W4412423988","https://openalex.org/W4413061389","https://openalex.org/W7125528673","https://openalex.org/W7126034194","https://openalex.org/W7126204246","https://openalex.org/W7128163300","https://openalex.org/W7133295553"],"related_works":[],"abstract_inverted_index":{"Few-shot":[0],"fine-grained":[1,22,86,207],"image":[2,208],"classification":[3,112,209],"remains":[4],"a":[5,47,97,109,153],"challenging":[6],"task":[7,156],"due":[8],"to":[9,26,34,50,84,133,157,184],"the":[10,15,73,101,104,120,143,173],"subtle":[11],"inter-class":[12],"variations":[13],"and":[14,32,54,60,125,137,161,193,202],"scarcity":[16,136],"of":[17],"labeled":[18],"data.":[19],"Existing":[20],"few-shot":[21,206],"methods":[23],"often":[24],"struggle":[25],"generalize":[27],"effectively":[28],"under":[29],"low-data":[30],"regimes":[31],"fail":[33],"discriminate":[35],"between":[36,122],"visually":[37],"similar":[38],"samples.":[39],"To":[40],"address":[41],"these":[42,94],"challenges,":[43],"we":[44],"propose":[45],"DistillCvT,":[46],"two-stage":[48,98],"framework":[49],"enhance":[51,158],"model":[52,105,149,175],"generalization":[53],"feature":[55,74,159],"discrimination":[56,160],"through":[57,96,181],"self-supervised":[58,154],"learning":[59],"self-distillation":[61,183],"within":[62],"prototypical":[63,110],"network":[64],"structure.":[65],"Convolutional":[66],"Vision":[67],"Transformer":[68],"(CvT)":[69],"is":[70,106,150],"employed":[71],"as":[72],"extractor,":[75],"which":[76],"integrates":[77],"convolutional":[78],"locality":[79],"with":[80,152,167],"transformer-based":[81],"global":[82,90],"modeling":[83],"capture":[85],"details":[87],"while":[88],"preserving":[89],"context.":[91],"DistillCvT":[92,198],"mitigates":[93],"issues":[95],"strategy.":[99],"In":[100,142],"first":[102],"stage,":[103,145],"trained":[107,151],"using":[108],"distance-based":[111],"loss,":[113],"where":[114],"class":[115,126,140],"probabilities":[116],"are":[117],"computed":[118],"from":[119,176],"distances":[121],"query":[123,170],"samples":[124,166],"prototypes,":[127],"complemented":[128],"by":[129,163],"standard":[130],"data":[131,135],"augmentation":[132],"mitigate":[134],"learn":[138],"discriminative":[139],"representations.":[141],"second":[144],"an":[146],"identical":[147],"student":[148],"jigsaw":[155],"robustness":[162],"aligning":[164],"support":[165],"their":[168],"augmented":[169],"counterparts.":[171],"Simultaneously,":[172],"teacher":[174],"stage":[177],"one":[178],"guides":[179],"it":[180],"logit-based":[182],"further":[185],"improve":[186],"generalization.":[187],"Experiments":[188],"on":[189],"CUB-200-2011,":[190],"Stanford":[191,194],"Dogs,":[192],"Cars":[195],"demonstrate":[196],"that":[197],"consistently":[199],"improves":[200],"performance":[201],"outperforms":[203],"recent":[204],"state-of-the-art":[205],"methods.":[210]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-18T00:00:00"}
