{"id":"https://openalex.org/W7214035917","doi":"https://doi.org/10.48550/arxiv.2609.24064","title":"Vision Transformers versus convolutional neural networks for fine-grained orchid genus identification in a species-rich, data-poor flora: a controlled benchmark on the Orchidaceae of New Guinea","display_name":"Vision Transformers versus convolutional neural networks for fine-grained orchid genus identification in a species-rich, data-poor flora: a controlled benchmark on the Orchidaceae of New Guinea","publication_year":2026,"publication_date":"2026-09-21","ids":{"openalex":"https://openalex.org/W7214035917","doi":"https://doi.org/10.48550/arxiv.2609.24064"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.24064","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24064","pdf_url":"https://arxiv.org/pdf/2609.24064","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.24064","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146170603","display_name":"Reza Saputra","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387154144","display_name":"National Research and Innovation Agency","ror":"https://ror.org/02hmjzt55","country_code":"ID","type":"government","lineage":["https://openalex.org/I4387154144"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Saputra, Reza","raw_affiliation_strings":["The Directorate of Scientific Collection Management , National Research and Innovation Agency (BRIN) , Republic of Indonesia ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Directorate of Scientific Collection Management , National Research and Innovation Agency (BRIN) , Republic of Indonesia ,","institution_ids":["https://openalex.org/I4387154144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031132940","display_name":"Diah Harnoni Apriyanti","orcid":"https://orcid.org/0000-0002-1673-7870","observed_orcids":["https://orcid.org/0000-0002-1673-7870"]},"institutions":[{"id":"https://openalex.org/I86467917","display_name":"James Cook University","ror":"https://ror.org/04gsp2c11","country_code":"AU","type":"education","lineage":["https://openalex.org/I86467917"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Apriyanti, Diah Harnoni","raw_affiliation_strings":["College of Science and Engineering , James Cook University. McGregor Rd , Smithfield , Cairns , QLD 4878 , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science and Engineering , James Cook University. McGregor Rd , Smithfield , Cairns , QLD 4878 , Australia","institution_ids":["https://openalex.org/I86467917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041232526","display_name":"Andr\u00e9 Schuiteman","orcid":"https://orcid.org/0000-0001-6701-8158","observed_orcids":["https://orcid.org/0000-0001-6701-8158"]},"institutions":[{"id":"https://openalex.org/I86467917","display_name":"James Cook University","ror":"https://ror.org/04gsp2c11","country_code":"AU","type":"education","lineage":["https://openalex.org/I86467917"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Schuiteman, Andr\u00e9","raw_affiliation_strings":["College of Science and Engineering , James Cook University. McGregor Rd , Smithfield , Cairns , QLD 4878 , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science and Engineering , James Cook University. McGregor Rd , Smithfield , Cairns , QLD 4878 , Australia","institution_ids":["https://openalex.org/I86467917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152456955","display_name":"Kurt Metzger","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86467917","display_name":"James Cook University","ror":"https://ror.org/04gsp2c11","country_code":"AU","type":"education","lineage":["https://openalex.org/I86467917"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Metzger, Kurt","raw_affiliation_strings":["College of Science and Engineering , James Cook University. McGregor Rd , Smithfield , Cairns , QLD 4878 , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science and Engineering , James Cook University. McGregor Rd , Smithfield , Cairns , QLD 4878 , Australia","institution_ids":["https://openalex.org/I86467917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148168531","display_name":"Ashley Field","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86467917","display_name":"James Cook University","ror":"https://ror.org/04gsp2c11","country_code":"AU","type":"education","lineage":["https://openalex.org/I86467917"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Field, Ashley","raw_affiliation_strings":["College of Science and Engineering , James Cook University. McGregor Rd , Smithfield , Cairns , QLD 4878 , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science and Engineering , James Cook University. McGregor Rd , Smithfield , Cairns , QLD 4878 , Australia","institution_ids":["https://openalex.org/I86467917"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031203900","display_name":"Katharina Nargar","orcid":"https://orcid.org/0000-0002-0459-5991","observed_orcids":["https://orcid.org/0000-0002-0459-5991"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nargar, Katharina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5115505772","display_name":"William Edwards","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387154144","display_name":"National Research and Innovation Agency","ror":"https://ror.org/02hmjzt55","country_code":"ID","type":"government","lineage":["https://openalex.org/I4387154144"]},{"id":"https://openalex.org/I86467917","display_name":"James Cook University","ror":"https://ror.org/04gsp2c11","country_code":"AU","type":"education","lineage":["https://openalex.org/I86467917"]}],"countries":["AU","ID"],"is_corresponding":false,"raw_author_name":"Edwards, William","raw_affiliation_strings":["College of Science and Engineering , James Cook University. McGregor Rd , Smithfield , Cairns , QLD 4878 , Australia","Gedung Kehati , KST Soekarno BRIN , Jl. Raya Jakarta -Bogor KM 46 , Cibinong , Kabupaten Bogor , Jawa Barat , 16911 , Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science and Engineering , James Cook University. McGregor Rd , Smithfield , Cairns , QLD 4878 , Australia","institution_ids":["https://openalex.org/I86467917"]},{"raw_affiliation_string":"Gedung Kehati , KST Soekarno BRIN , Jl. Raya Jakarta -Bogor KM 46 , Cibinong , Kabupaten Bogor , Jawa Barat , 16911 , Indonesia","institution_ids":["https://openalex.org/I4387154144"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8730000257492065,"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":0.8730000257492065,"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":0.08349999785423279,"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/T10616","display_name":"Smart Agriculture and AI","score":0.018300000578165054,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/orchids","display_name":"Orchidaceae","score":0.9369999766349792},{"id":"https://openalex.org/keywords/new-guinea-flora","display_name":"New Guinea flora","score":0.7689999938011169},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.7689999938011169},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.8550000190734863},{"id":"https://openalex.org/keywords/dinov2","display_name":"DINOv2","score":0.8980000019073486},{"id":"https://openalex.org/keywords/self-supervised-pretraining","display_name":"self-supervised pre-training","score":0.9309999942779541},{"id":"https://openalex.org/keywords/fine-grained-classification","display_name":"fine-grained classification","score":0.7450000047683716},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"image retrieval","score":0.7839999794960022},{"id":"https://openalex.org/keywords/faiss","display_name":"FAISS","score":0.6620000004768372},{"id":"https://openalex.org/keywords/open-set-detection","display_name":"open-set detection","score":0.7789999842643738},{"id":"https://openalex.org/keywords/temperature-scaling","display_name":"temperature scaling","score":0.8190000057220459},{"id":"https://openalex.org/keywords/calibration","display_name":"calibration","score":0.5180000066757202}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6209999918937683},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5595999956130981},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.482699990272522},{"id":"https://openalex.org/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.39169999957084656},{"id":"https://openalex.org/C2781370656","wikidata":"https://www.wikidata.org/wiki/Q25308","display_name":"Orchidaceae","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C3017739461","wikidata":"https://www.wikidata.org/wiki/Q40285","display_name":"New guinea","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.24064","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24064","pdf_url":"https://arxiv.org/pdf/2609.24064","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.24064","doi":"https://doi.org/10.48550/arxiv.2609.24064","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.24064","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.24064","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.24064","pdf_url":"https://arxiv.org/pdf/2609.24064","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214035917.pdf","grobid_xml":"https://content.openalex.org/works/W7214035917.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1519412068","https://openalex.org/W1995945562","https://openalex.org/W2099307030","https://openalex.org/W2273396394","https://openalex.org/W2531327146","https://openalex.org/W2568155635","https://openalex.org/W2593864460","https://openalex.org/W2626967530","https://openalex.org/W2780868291","https://openalex.org/W2950181225","https://openalex.org/W2963691377","https://openalex.org/W2991744714","https://openalex.org/W3024386879","https://openalex.org/W3026842959","https://openalex.org/W3047159966","https://openalex.org/W3084578230","https://openalex.org/W3090048552","https://openalex.org/W3092008126","https://openalex.org/W3094502228","https://openalex.org/W3106646540","https://openalex.org/W3135367836","https://openalex.org/W3139434170","https://openalex.org/W3145444543","https://openalex.org/W3159481202","https://openalex.org/W3170360335","https://openalex.org/W3195830874","https://openalex.org/W3198924756","https://openalex.org/W3207447946","https://openalex.org/W4205759668","https://openalex.org/W4281728047","https://openalex.org/W4297312203","https://openalex.org/W4313151233","https://openalex.org/W4361025570","https://openalex.org/W4366208220","https://openalex.org/W4366352743","https://openalex.org/W4366991531","https://openalex.org/W4386032416","https://openalex.org/W4386076493","https://openalex.org/W4392145825","https://openalex.org/W4402770330","https://openalex.org/W4407132269","https://openalex.org/W4407860901","https://openalex.org/W4414855527","https://openalex.org/W4415085313"],"related_works":["https://openalex.org/W2515106546","https://openalex.org/W4403936928","https://openalex.org/W7169501786","https://openalex.org/W4205704153","https://openalex.org/W3197716167","https://openalex.org/W4393026926","https://openalex.org/W7127191257","https://openalex.org/W4386032416","https://openalex.org/W7160402735","https://openalex.org/W4285328933"],"abstract_inverted_index":{"New":[0,241],"Guinea":[1,242],"is":[2,219,233],"the":[3,61,132],"world's":[4],"richest":[5],"island":[6],"flora":[7],"(~2,856":[8],"orchid":[9],"species),":[10],"yet":[11],"most":[12],"species":[13,75,122,180],"are":[14,38],"represented":[15],"by":[16,161],"only":[17],"a":[18,55,64,104,201,246],"handful":[19],"of":[20,63,73,108,127,164,182,187],"photographs,":[21],"far":[22],"fewer":[23],"than":[24],"direct":[25],"species-level":[26],"classification":[27],"requires.":[28],"Methods":[29],"for":[30,224,249],"fine-grained":[31,225],"identification":[32,226],"in":[33,227],"such":[34],"species-rich,":[35,228],"data-poor":[36,229],"floras":[37],"needed,":[39],"and":[40,47,91,114,124,150,184,200],"it":[41],"remains":[42],"unclear":[43],"which":[44],"backbone":[45,214],"architecture":[46],"pretraining":[48,153,158],"strategy":[49,223],"best":[50,133],"support":[51],"them.":[52],"We":[53,78],"built":[54],"two-stage":[56],"system":[57,232],"that":[58],"first":[59],"predicts":[60],"genus":[62,134,185],"query":[65],"photograph,":[66],"then":[67],"retrieves":[68],"visually":[69],"similar":[70],"reference":[71],"images":[72],"candidate":[74],"using":[76],"FAISS.":[77],"compared":[79],"four":[80],"pretrained":[81],"backbones":[82],"--":[83,97],"two":[84,92,170],"Vision":[85],"Transformers":[86],"(ViTs;":[87],"DINOv2,":[88],"BioCLIP":[89],"2)":[90,160],"CNNs":[93],"(ConvNeXt":[94],"V2-L,":[95],"EfficientNetV2-L)":[96],"fine-tuned":[98],"under":[99],"an":[100,220,236],"identical":[101],"protocol":[102],"on":[103,169],"fixed,":[105],"species-stratified":[106],"partition":[107],"16,701":[109],"photographs":[110],"spanning":[111],"120":[112],"genera":[113,172,207],"1,350":[115],"species,":[116],"assessing":[117],"accuracy,":[118],"calibration,":[119],"error":[120,175],"structure,":[121],"retrieval,":[123],"open-set":[125,203],"detection":[126],"novel":[128],"genera.":[129],"DINOv2":[130,177],"attained":[131],"performance":[135],"(macro":[136],"top-1":[137,143],"66.9%,":[138],"95%":[139],"CI":[140],"63.7-70.6;":[141],"global":[142],"88.9%);":[144],"both":[145,148],"ViTs":[146],"outranked":[147],"CNNs,":[149],"general-purpose":[151],"self-supervised":[152,212],"(DINOv2)":[154],"outperformed":[155],"domain-matched":[156],"biological":[157],"(BioCLIP":[159],"7.1":[162],"points":[163],"macro":[165],"top-1.":[166],"Errors":[167],"concentrated":[168],"abundant":[171],"acting":[173],"as":[174,235],"attractors.":[176],"embeddings":[178],"achieved":[179],"Recall@5":[181,186],"86.6%":[183],"98.7%;":[188],"temperature":[189],"scaling":[190],"reduced":[191],"every":[192],"backbone's":[193],"Expected":[194],"Calibration":[195],"Error":[196],"to":[197],"about":[198],"0.03;":[199],"distance-based":[202],"gate":[204],"flagged":[205],"unseen":[206],"(mean":[208],"AUROC":[209],"0.958).":[210],"A":[211],"Vision-Transformer":[213],"combined":[215],"with":[216],"embedding":[217],"retrieval":[218],"effective,":[221],"deployable":[222],"floras.":[230],"The":[231],"released":[234],"open":[237],"web":[238],"application":[239],"(the":[240],"Orchid":[243],"Identifier),":[244],"offering":[245],"practical":[247],"template":[248],"other":[250],"hyperdiverse,":[251],"under-documented":[252],"taxa.":[253]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-23T00:00:00"}