{"id":"https://openalex.org/W7120155256","doi":"https://doi.org/10.48550/arxiv.2601.04352","title":"Comparative Analysis of Custom CNN Architectures versus Pre-trained Models and Transfer Learning: A Study on Five Bangladesh Datasets","display_name":"Comparative Analysis of Custom CNN Architectures versus Pre-trained Models and Transfer Learning: A Study on Five Bangladesh Datasets","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7120155256","doi":"https://doi.org/10.48550/arxiv.2601.04352"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.04352","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.04352","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.04352","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117109486","display_name":"Ibrahim Tanvir","orcid":null},"institutions":[{"id":"https://openalex.org/I205746353","display_name":"University of Dhaka","ror":"https://ror.org/05wv2vq37","country_code":"BD","type":"education","lineage":["https://openalex.org/I205746353"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Tanvir, Ibrahim","raw_affiliation_strings":["University of Dhaka"],"affiliations":[{"raw_affiliation_string":"University of Dhaka","institution_ids":["https://openalex.org/I205746353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122480194","display_name":"Alif Ruslan","orcid":null},"institutions":[{"id":"https://openalex.org/I205746353","display_name":"University of Dhaka","ror":"https://ror.org/05wv2vq37","country_code":"BD","type":"education","lineage":["https://openalex.org/I205746353"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Ruslan, Alif","raw_affiliation_strings":["University of Dhaka"],"affiliations":[{"raw_affiliation_string":"University of Dhaka","institution_ids":["https://openalex.org/I205746353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093910592","display_name":"Sartaj Solaiman","orcid":null},"institutions":[{"id":"https://openalex.org/I205746353","display_name":"University of Dhaka","ror":"https://ror.org/05wv2vq37","country_code":"BD","type":"education","lineage":["https://openalex.org/I205746353"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Solaiman, Sartaj","raw_affiliation_strings":["University of Dhaka"],"affiliations":[{"raw_affiliation_string":"University of Dhaka","institution_ids":["https://openalex.org/I205746353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5117109486"],"corresponding_institution_ids":["https://openalex.org/I205746353"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.6021999716758728,"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":0.6021999716758728,"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":0.23680000007152557,"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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.01549999974668026,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7730000019073486},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7402999997138977},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6105999946594238},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5703999996185303},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4927999973297119},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4853000044822693},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44029998779296875},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.42399999499320984}],"concepts":[{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7730000019073486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567999958992004},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7402999997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6696000099182129},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6105999946594238},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5703999996185303},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5598000288009644},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4927999973297119},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.42399999499320984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.04352","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.04352","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.04352","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.04352","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,139],"study":[1],"presents":[2],"a":[3],"comprehensive":[4],"comparative":[5],"analysis":[6],"of":[7],"custom-built":[8],"Convolutional":[9],"Neural":[10],"Networks":[11],"(CNNs)":[12],"against":[13],"popular":[14],"pre-trained":[15,114,122],"architectures":[16],"(ResNet-18":[17],"and":[18,24,51,72,116,158],"VGG-16)":[19],"using":[20],"both":[21,66],"feature":[22,73],"extraction":[23,74],"transfer":[25,60,125],"learning":[26,61,126,150],"approaches.":[27],"We":[28],"evaluated":[29],"these":[30],"models":[31,123],"across":[32,84],"five":[33],"diverse":[34],"image":[35],"classification":[36,133],"datasets":[37],"from":[38,70,80],"Bangladesh:":[39],"Footpath":[40],"Vision,":[41],"Auto":[42],"Rickshaw":[43],"Detection,":[44],"Mango":[45],"Image":[46],"Classification,":[47],"Paddy":[48],"Variety":[49],"Recognition,":[50],"Road":[52,97],"Damage":[53,98],"Detection.":[54],"Our":[55],"experimental":[56],"results":[57],"demonstrate":[58],"that":[59],"with":[62,89,124,135],"fine-tuning":[63,90],"consistently":[64],"outperforms":[65],"custom":[67,102],"CNNs":[68,103],"built":[69],"scratch":[71],"methods,":[75],"achieving":[76],"accuracy":[77,94],"improvements":[78],"ranging":[79],"3%":[81],"to":[82],"76%":[83],"different":[85],"datasets.":[86],"Notably,":[87],"ResNet-18":[88],"achieved":[91],"perfect":[92],"100%":[93],"on":[95,119,131,153],"the":[96],"BD":[99],"dataset.":[100],"While":[101],"offer":[104],"advantages":[105],"in":[106,146],"model":[107],"size":[108],"(3.4M":[109],"parameters":[110],"vs.":[111],"11-134M":[112],"for":[113,144],"models)":[115],"training":[117,137],"efficiency":[118],"simpler":[120],"tasks,":[121],"provide":[127],"superior":[128],"performance,":[129],"particularly":[130],"complex":[132],"tasks":[134],"limited":[136],"data.":[138],"research":[140],"provides":[141],"practical":[142],"insights":[143],"practitioners":[145],"selecting":[147],"appropriate":[148],"deep":[149],"approaches":[151],"based":[152],"dataset":[154],"characteristics,":[155],"computational":[156],"resources,":[157],"performance":[159],"requirements.":[160]},"counts_by_year":[],"updated_date":"2026-01-10T23:44:22.266649","created_date":"2026-01-10T00:00:00"}