{"id":"https://openalex.org/W7125116009","doi":"https://doi.org/10.1109/cbmi66578.2025.11339312","title":"Beyond CNNs: Efficient Fine-Tuning of Multi-Modal LLMs for Object Detection on Low-Data Regimes","display_name":"Beyond CNNs: Efficient Fine-Tuning of Multi-Modal LLMs for Object Detection on Low-Data Regimes","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7125116009","doi":"https://doi.org/10.1109/cbmi66578.2025.11339312"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060898316","display_name":"Nirmal Elamon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210106647","display_name":"Expedia Group (United States)","ror":"https://ror.org/01sh85g09","country_code":"US","type":"company","lineage":["https://openalex.org/I4210106647"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nirmal Elamon","raw_affiliation_strings":["Artificial Creative intelligence (ACI) Expedia Group,Seattle,USA"],"affiliations":[{"raw_affiliation_string":"Artificial Creative intelligence (ACI) Expedia Group,Seattle,USA","institution_ids":["https://openalex.org/I4210106647"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007304484","display_name":"Rouzbeh Davoudi","orcid":"https://orcid.org/0000-0003-4999-1661"},"institutions":[{"id":"https://openalex.org/I4210106647","display_name":"Expedia Group (United States)","ror":"https://ror.org/01sh85g09","country_code":"US","type":"company","lineage":["https://openalex.org/I4210106647"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rouzbeh Davoudi","raw_affiliation_strings":["Artificial Creative intelligence (ACI) Expedia Group,Seattle,USA"],"affiliations":[{"raw_affiliation_string":"Artificial Creative intelligence (ACI) Expedia Group,Seattle,USA","institution_ids":["https://openalex.org/I4210106647"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060898316"],"corresponding_institution_ids":["https://openalex.org/I4210106647"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70196274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6672999858856201,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6672999858856201,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.20160000026226044,"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":0.01590000092983246,"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/object-detection","display_name":"Object detection","score":0.6065999865531921},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5194000005722046},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41200000047683716},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39469999074935913},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.35569998621940613},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3109000027179718},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3057999908924103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6549000144004822},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6065999865531921},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4805999994277954},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4203000068664551},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.39899998903274536},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36070001125335693},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2963037989","https://openalex.org/W2998847993"],"related_works":[],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,61,82,98,108,143,169,190],"object":[3,195],"detection":[4,102,196],"and":[5,18,29,50,90,172,187,198,234],"understanding":[6,158],"is":[7,111],"rapidly":[8],"evolving,":[9],"driven":[10],"by":[11],"advances":[12],"in":[13,67,103,206,214,228,236],"both":[14],"traditional":[15,84],"CNN-based":[16,137],"models":[17,23,151,226],"emerging":[19],"multi-modal":[20,88,92,204],"large":[21],"language":[22],"(LLMs).":[24],"While":[25],"CNNs":[26],"like":[27],"ResNet":[28],"YOLO":[30],"remain":[31],"highly":[32],"effective":[33],"for":[34,155,193,202],"image-based":[35],"tasks,":[36],"recent":[37],"transformer-based":[38],"LLMs":[39,62,93,114],"introduce":[40],"new":[41],"capabilities":[42],"such":[43],"as":[44],"dynamic":[45],"context":[46],"reasoning,":[47],"language-guided":[48,150],"prompts,":[49],"holistic":[51],"scene":[52],"understanding.":[53],"However,":[54],"when":[55],"used":[56,222],"out-of-the-box,":[57],"the":[58,95,166,185,220,225],"full":[59],"potential":[60],"remains":[63],"underexploited,":[64],"often":[65],"resulting":[66],"suboptimal":[68],"performance":[69],"on":[70,94,119],"specialized":[71],"visual":[72,157,208],"tasks.":[73],"In":[74],"this":[75,215],"work,":[76],"we":[77,217],"conduct":[78],"a":[79],"comprehensive":[80],"comparison":[81],"fine-tuned":[83,91,118],"CNNs,":[85],"zero-shot":[86],"pre-trained":[87],"LLMs,":[89],"challenging":[96],"task":[97],"artificial":[99],"text":[100],"overlay":[101],"images.":[104],"A":[105],"key":[106],"contribution":[107],"our":[109,162,229],"study":[110],"demonstrating":[112],"that":[113,139],"can":[115,152],"be":[116,153],"effectively":[117],"very":[120],"limited":[121],"data":[122,188],"(fewer":[123],"than":[124],"1,000":[125],"images)":[126],"to":[127,130,165,223],"achieve":[128],"up":[129],"36%":[131],"accuracy":[132],"improvement,":[133],"matching":[134],"or":[135],"surpassing":[136],"baselines":[138],"typically":[140],"require":[141],"orders":[142],"magnitude":[144],"more":[145],"data.":[146],"By":[147],"exploring":[148],"how":[149],"adapted":[154],"precise":[156],"with":[159],"minimal":[160],"supervision,":[161],"work":[163],"contributes":[164],"broader":[167],"effort":[168],"bridging":[170],"vision":[171],"language,":[173],"offering":[174],"novel":[175],"insights":[176],"into":[177],"efficient":[178],"cross-modal":[179],"learning":[180],"strategies.":[181],"These":[182],"findings":[183],"highlight":[184],"adaptability":[186],"efficiency":[189],"LLM-based":[191],"approaches":[192],"real-world":[194],"tasks":[197],"provide":[199],"actionable":[200],"guidance":[201],"applying":[203],"transformers":[205],"low-resource":[207],"environments.":[209],"To":[210],"support":[211],"continued":[212],"progress":[213],"area,":[216],"have":[218],"made":[219],"code":[221],"fine-tune":[224],"available":[227],"GitHub,":[230],"enabling":[231],"future":[232],"improvements":[233],"reuse":[235],"related":[237],"applications.":[238],"1":[239]},"counts_by_year":[],"updated_date":"2026-01-22T23:33:04.759266","created_date":"2026-01-22T00:00:00"}