{"id":"https://openalex.org/W7225748020","doi":"https://doi.org/10.21203/rs.3.rs-11675885/v1","title":"Beyond Accuracy Rankings: Cross-Dataset Stability and Computational Cost in Plant Disease Classification","display_name":"Beyond Accuracy Rankings: Cross-Dataset Stability and Computational Cost in Plant Disease Classification","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225748020","doi":"https://doi.org/10.21203/rs.3.rs-11675885/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11675885/v1","doi":"https://doi.org/10.21203/rs.3.rs-11675885/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11675885/v1","pdf_url":"https://www.researchsquare.com/article/rs-11675885/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-11675885/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157929045","display_name":"Nitin Kumar","orcid":"https://orcid.org/0009-0007-3661-859X","observed_orcids":["https://orcid.org/0009-0007-3661-859X"]},"institutions":[{"id":"https://openalex.org/I110360157","display_name":"Lovely Professional University","ror":"https://ror.org/00et6q107","country_code":"IN","type":"education","lineage":["https://openalex.org/I110360157"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nitin Kumar","raw_affiliation_strings":["Lovely Professional University"],"raw_orcid":"https://orcid.org/0009-0007-3661-859X","affiliations":[{"raw_affiliation_string":"Lovely Professional University","institution_ids":["https://openalex.org/I110360157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110884052","display_name":"Sakshi Dua","orcid":"https://orcid.org/0000-0002-8143-2168","observed_orcids":["https://orcid.org/0000-0002-8143-2168"]},"institutions":[{"id":"https://openalex.org/I110360157","display_name":"Lovely Professional University","ror":"https://ror.org/00et6q107","country_code":"IN","type":"education","lineage":["https://openalex.org/I110360157"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sakshi Dua","raw_affiliation_strings":["Lovely Professional University"],"raw_orcid":"https://orcid.org/0000-0002-8143-2168","affiliations":[{"raw_affiliation_string":"Lovely Professional University","institution_ids":["https://openalex.org/I110360157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I110360157"],"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/T10616","display_name":"Smart Agriculture and AI","score":0.9907000064849854,"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"}},"topics":[{"id":"https://openalex.org/T10616","display_name":"Smart Agriculture and AI","score":0.9907000064849854,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.009100000374019146,"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":9.999999747378752e-05,"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":[],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5942000150680542},{"id":"https://openalex.org/C186282968","wikidata":"https://www.wikidata.org/wiki/Q1434261","display_name":"McNemar's test","level":2,"score":0.5913000106811523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5645999908447266},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5561000108718872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5187000036239624},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.49320000410079956},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.492000013589859},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43860000371932983},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.39590001106262207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39329999685287476},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3253999948501587},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C3019235130","wikidata":"https://www.wikidata.org/wiki/Q188956","display_name":"Plant disease","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26440000534057617},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11675885/v1","doi":"https://doi.org/10.21203/rs.3.rs-11675885/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11675885/v1","pdf_url":"https://www.researchsquare.com/article/rs-11675885/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11675885/v1","doi":"https://doi.org/10.21203/rs.3.rs-11675885/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11675885/v1","pdf_url":"https://www.researchsquare.com/article/rs-11675885/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225748020.pdf","grobid_xml":"https://content.openalex.org/works/W7225748020.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2277854822","https://openalex.org/W2339460098","https://openalex.org/W2473156356","https://openalex.org/W2789255992","https://openalex.org/W2989646980","https://openalex.org/W3125682525","https://openalex.org/W3187567638","https://openalex.org/W4312910656","https://openalex.org/W4319998068","https://openalex.org/W4322740557","https://openalex.org/W4323927417","https://openalex.org/W4390873031","https://openalex.org/W4393851611","https://openalex.org/W4405558966","https://openalex.org/W4405904683","https://openalex.org/W4406488712","https://openalex.org/W4409103163","https://openalex.org/W4412939586","https://openalex.org/W4412951505","https://openalex.org/W7130729265","https://openalex.org/W7141120248","https://openalex.org/W7203911227"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"On":[1],"a":[2,217,241,247],"specific":[3,225],"dataset,":[4],"achieving":[5],"high":[6],"accuracy":[7,27,145,153],"in":[8],"plant":[9],"disease":[10],"classification":[11,119],"with":[12,51,208,246],"CNN":[13],"is":[14,216,237],"possible,":[15],"but":[16],"it":[17,236],"should":[18],"also":[19],"be":[20],"evaluated":[21],"on":[22,32,174],"other":[23],"datasets":[24],"and":[25,47,69,87,111,130,148,164,190,223],"the":[26,29,33,42,85,98,118,122,125,137,142,160,183,191,211,220],"of":[28,44,74,94,97,124,178,186,194,213,219,230,243,249],"CNNs":[30],"depend":[31],"cost":[34],"as":[35,134],"well.":[36],"This":[37],"study":[38],"tries":[39],"to":[40,67,83,116,210,228,239],"compare":[41],"performance":[43,245],"ResNet-50,":[45],"MobileNetV2":[46,173,181],"EfficientNet":[48],"B0":[49],"architectures":[50],"frozen":[52],"feature":[53],"transfer":[54],"learning":[55],"approach.":[56],"The":[57,108,151,197,232],"38-class":[58],"New":[59],"Plant":[60],"Diseases":[61],"Dataset":[62],"(Augmented)":[63],"has":[64],"been":[65,81],"used":[66,82,89,101,115,133],"train":[68,84],"internally":[70],"validate":[71],"models":[72,86],"consisting":[73],"70,295":[75],"images":[76,96],"from":[77],"which":[78],"56,236":[79],"have":[80],"14,059":[88],"for":[90,102,105,136],"tests.":[91],"A":[92],"total":[93],"146":[95],"PlantDoc":[99],"were":[100,114,132],"external":[103,221],"evaluation":[104],"17":[106],"classes.":[107],"accuracy,":[109],"macro-F1,":[110],"weighted-F1":[112],"score":[113,146],"measure":[117,242,248],"performance,":[120],"while":[121,159],"number":[123,185],"parameters,":[126],"batch-one":[127],"inference":[128,166],"latency":[129,167],"throughput":[131,193],"measurement":[135],"computational":[138,250],"efficiency.":[139,251],"ResNet-50":[140,158],"got":[141],"best":[143,152,161],"internal":[144],"(96.33%)":[147],"macro-F1":[149,162],"(96.22%).":[150],"(21.23%)":[154],"was":[155,170],"obtained":[156,171],"by":[157,172],"(22.48%)":[163],"measured":[165,179],"(4.97":[168],"ms)":[169],"PlantDoc.":[175],"In":[176],"terms":[177],"throughput,":[180],"had":[182],"lowest":[184],"parameters":[187],"(2.27":[188],"million)":[189],"highest":[192],"201.2":[195],"images/s.":[196],"pairwise":[198],"McNemar":[199],"tests":[200],"did":[201],"not":[202],"reveal":[203],"any":[204],"statistically":[205],"significant":[206],"differences":[207],"respect":[209],"prediction":[212],"correctness.":[214],"There":[215],"restriction":[218],"sample":[222],"hardware":[224],"benchmarking":[226],"leading":[227],"limitation":[229],"generalization.":[231],"results":[233],"suggest":[234],"that":[235],"worthwhile":[238],"combine":[240],"predictive":[244]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}