{"id":"https://openalex.org/W4411270602","doi":"https://doi.org/10.1109/access.2025.3579420","title":"When Multimodal Large Language Models Meet Computer Vision: Progressive GPT Fine-Tuning and Stress Testing","display_name":"When Multimodal Large Language Models Meet Computer Vision: Progressive GPT Fine-Tuning and Stress Testing","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411270602","doi":"https://doi.org/10.1109/access.2025.3579420"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3579420","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3579420","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3579420","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077820227","display_name":"Konstantinos I. Roumeliotis","orcid":"https://orcid.org/0000-0002-8098-1616"},"institutions":[{"id":"https://openalex.org/I158716096","display_name":"University of Peloponnese","ror":"https://ror.org/04d4d3c02","country_code":"GR","type":"education","lineage":["https://openalex.org/I158716096"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos I. Roumeliotis","raw_affiliation_strings":["Department of Informatics and Telecommunications, Faculty of Economics and Technology, University of Peloponnese, Tripoli, Greece","Department of Informatics and Telecommunications, Faculty of Economics and Technology, University of the Peloponnese, Tripoli, Greece"],"raw_orcid":"https://orcid.org/0000-0002-8098-1616","affiliations":[{"raw_affiliation_string":"Department of Informatics and Telecommunications, Faculty of Economics and Technology, University of Peloponnese, Tripoli, Greece","institution_ids":["https://openalex.org/I158716096"]},{"raw_affiliation_string":"Department of Informatics and Telecommunications, Faculty of Economics and Technology, University of the Peloponnese, Tripoli, Greece","institution_ids":["https://openalex.org/I158716096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039512085","display_name":"Nikolaos D. Tselikas","orcid":"https://orcid.org/0000-0001-5799-3558"},"institutions":[{"id":"https://openalex.org/I158716096","display_name":"University of Peloponnese","ror":"https://ror.org/04d4d3c02","country_code":"GR","type":"education","lineage":["https://openalex.org/I158716096"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikolaos D. Tselikas","raw_affiliation_strings":["Department of Informatics and Telecommunications, Faculty of Economics and Technology, University of Peloponnese, Tripoli, Greece","Department of Informatics and Telecommunications, Faculty of Economics and Technology, University of the Peloponnese, Tripoli, Greece"],"raw_orcid":"https://orcid.org/0000-0001-5799-3558","affiliations":[{"raw_affiliation_string":"Department of Informatics and Telecommunications, Faculty of Economics and Technology, University of Peloponnese, Tripoli, Greece","institution_ids":["https://openalex.org/I158716096"]},{"raw_affiliation_string":"Department of Informatics and Telecommunications, Faculty of Economics and Technology, University of the Peloponnese, Tripoli, Greece","institution_ids":["https://openalex.org/I158716096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080101227","display_name":"Dimitrios \u039a. Nasiopoulos","orcid":"https://orcid.org/0000-0001-7386-1029"},"institutions":[{"id":"https://openalex.org/I109954829","display_name":"Agricultural University of Athens","ror":"https://ror.org/03xawq568","country_code":"GR","type":"education","lineage":["https://openalex.org/I109954829"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios K. Nasiopoulos","raw_affiliation_strings":["Department of Agribusiness and Supply Chain Management, School of Applied Economics and Social Sciences, Agricultural University of Athens, Athens, Greece"],"raw_orcid":"https://orcid.org/0000-0001-7386-1029","affiliations":[{"raw_affiliation_string":"Department of Agribusiness and Supply Chain Management, School of Applied Economics and Social Sciences, Agricultural University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I109954829"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":5.584,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95516811,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"106155","last_page":"106174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9682000279426575,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9682000279426575,"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/computer-science","display_name":"Computer science","score":0.7149991989135742},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5935589075088501},{"id":"https://openalex.org/keywords/stress-testing","display_name":"Stress testing (software)","score":0.4681164622306824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3719659447669983},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3307517170906067},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21607306599617004}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7149991989135742},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5935589075088501},{"id":"https://openalex.org/C7515471","wikidata":"https://www.wikidata.org/wiki/Q1936882","display_name":"Stress testing (software)","level":2,"score":0.4681164622306824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3719659447669983},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3307517170906067},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21607306599617004},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3579420","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3579420","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:af910cf682914459976dcba81a8cafb8","is_oa":true,"landing_page_url":"https://doaj.org/article/af910cf682914459976dcba81a8cafb8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 106155-106174 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3579420","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3579420","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320318628","display_name":"Hellenic Academic Libraries Link","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2003661472","https://openalex.org/W2108598243","https://openalex.org/W2622826443","https://openalex.org/W2901742274","https://openalex.org/W2910688461","https://openalex.org/W2912849458","https://openalex.org/W2944008497","https://openalex.org/W3016785712","https://openalex.org/W3034060995","https://openalex.org/W3034563136","https://openalex.org/W3036444709","https://openalex.org/W3045553371","https://openalex.org/W3082931737","https://openalex.org/W3091946902","https://openalex.org/W3110110324","https://openalex.org/W3162728894","https://openalex.org/W3166701446","https://openalex.org/W3173291597","https://openalex.org/W4205172069","https://openalex.org/W4213019189","https://openalex.org/W4233506525","https://openalex.org/W4281645081","https://openalex.org/W4312241447","https://openalex.org/W4367295893","https://openalex.org/W4388723259","https://openalex.org/W4391422700","https://openalex.org/W4391738137","https://openalex.org/W4393028958","https://openalex.org/W4400487981","https://openalex.org/W4401764365","https://openalex.org/W4402727337","https://openalex.org/W4403277141","https://openalex.org/W4403791574","https://openalex.org/W4404002404","https://openalex.org/W4404140398","https://openalex.org/W4406857925","https://openalex.org/W4407419818","https://openalex.org/W4408190450","https://openalex.org/W4408400373","https://openalex.org/W4408609408","https://openalex.org/W4409443197","https://openalex.org/W6782151383","https://openalex.org/W6857901785","https://openalex.org/W6859186507"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"The":[0],"rapid":[1],"evolution":[2],"of":[3,13,33,53,153,169,222],"Multimodal":[4],"Large":[5,248],"Language":[6,249],"Models":[7,250],"(LLMs)":[8],"has":[9],"redefined":[10],"the":[11,31,51,136,160,176],"landscape":[12],"artificial":[14],"intelligence,":[15],"with":[16,138,172,213,229],"OpenAI\u2019s":[17],"GPT-4o":[18,34,54],"representing":[19],"a":[20,39,68,83,132,151,167,219,270],"transformative":[21],"leap":[22],"in":[23,42,226,251,261],"multimodal":[24,55,79,207,247,272,277],"learning":[25,72,157,204,208,228,278],"and":[26,94,109,119,127,140,156,175,189,202,218,240,279],"processing.":[27],"This":[28],"study":[29],"pioneers":[30],"fine-tuning":[32,73,193,256],"on":[35,63],"image":[36,90],"data,":[37],"addressing":[38],"critical":[40],"gap":[41],"evaluating":[43],"its":[44,224,267],"performance":[45,197],"beyond":[46],"zero-shot":[47],"capabilities.":[48],"It":[49],"investigates":[50],"potential":[52,268],"LLM":[56],"for":[57,102,146,184,245,275],"computer":[58,262],"vision":[59,263],"classification":[60,264],"tasks,":[61,265],"focusing":[62],"e-commerce":[64],"product":[65],"categorization":[66],"through":[67],"novel,":[69],"progressive,":[70],"few-shot":[71,227],"framework.":[74],"Leveraging":[75],"GPT-4o\u2019s":[76,206,254],"newly":[77],"available":[78],"capabilities,":[80],"we":[81,134],"implemented":[82],"four-phase":[84],"progressive":[85,255],"training":[86,103],"procedure":[87],"across":[88],"varying":[89],"resolutions":[91],"(100,":[92],"200,":[93],"400":[95],"pixels).":[96],"Each":[97],"phase":[98],"was":[99],"rigorously":[100],"evaluated":[101],"duration,":[104],"computational":[105],"cost,":[106],"loss":[107],"metrics,":[108],"validation":[110],"performance.":[111],"Predictions":[112],"were":[113],"assessed":[114],"using":[115,159],"accuracy,":[116],"precision,":[117],"recall,":[118],"F1-score":[120],"metrics":[121],"while":[122],"closely":[123],"monitoring":[124],"prediction":[125],"costs":[126],"processing":[128],"time.":[129],"To":[130],"establish":[131],"benchmark,":[133],"replicated":[135],"process":[137],"ResNet-50":[139,188],"ConvNeXt-tiny":[141,190],"models,":[142],"applying":[143],"Bayesian":[144],"optimization":[145],"hyperparameter":[147],"tuning.":[148],"We":[149],"explored":[150],"range":[152],"batch":[154,200,220],"sizes":[155,201],"rates":[158],"Optuna":[161],"library,":[162],"conducting":[163],"100":[164],"trials":[165],"over":[166],"maximum":[168],"50":[170],"epochs":[171,217],"early":[173],"stopping":[174],"successive":[177],"halving":[178],"pruner":[179],"to":[180],"identify":[181],"optimal":[182],"configurations":[183],"each":[185],"model.":[186],"Although":[187],"exhibited":[191],"lower":[192,203],"costs,":[194],"achieving":[195],"comparable":[196],"required":[198],"larger":[199],"rates.":[205],"approach":[209,257],"achieved":[210],"87%":[211],"accuracy":[212],"minimal":[214],"training\u2014just":[215],"three":[216],"size":[221],"one\u2014highlighting":[223],"efficiency":[225],"limited":[230],"labeled":[231],"data.":[232],"Our":[233],"findings":[234],"highlight":[235],"key":[236],"trade-offs":[237],"between":[238],"cost-efficiency":[239],"performance,":[241],"offering":[242],"actionable":[243],"insights":[244],"deploying":[246],"resource-constrained":[252],"scenarios.":[253],"showed":[258],"promising":[259],"results":[260],"suggesting":[266],"as":[269],"scalable,":[271],"AI":[273],"tool":[274],"real-world":[276],"vision-based":[280],"applications.":[281]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}