{"id":"https://openalex.org/W4405072733","doi":"https://doi.org/10.3390/make6040133","title":"Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks","display_name":"Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4405072733","doi":"https://doi.org/10.3390/make6040133"},"language":"en","primary_location":{"id":"doi:10.3390/make6040133","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make6040133","pdf_url":"https://www.mdpi.com/2504-4990/6/4/133/pdf?version=1733145003","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/6/4/133/pdf?version=1733145003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044579966","display_name":"Nermeen Abou Baker","orcid":"https://orcid.org/0000-0002-9683-5920"},"institutions":[{"id":"https://openalex.org/I4210123225","display_name":"Ruhr West University of Applied Sciences","ror":"https://ror.org/02nkxrq89","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210123225"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nermeen Abou Baker","raw_affiliation_strings":["Computer Science Department, Ruhr West University of Applied Sciences, L\u00fctzowstra\u00dfe 5, 46236 Bottrop, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9683-5920","affiliations":[{"raw_affiliation_string":"Computer Science Department, Ruhr West University of Applied Sciences, L\u00fctzowstra\u00dfe 5, 46236 Bottrop, Germany","institution_ids":["https://openalex.org/I4210123225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032719063","display_name":"David Rohrschneider","orcid":"https://orcid.org/0009-0003-4693-3797"},"institutions":[{"id":"https://openalex.org/I4210123225","display_name":"Ruhr West University of Applied Sciences","ror":"https://ror.org/02nkxrq89","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210123225"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"David Rohrschneider","raw_affiliation_strings":["Computer Science Department, Ruhr West University of Applied Sciences, L\u00fctzowstra\u00dfe 5, 46236 Bottrop, Germany"],"raw_orcid":"https://orcid.org/0009-0003-4693-3797","affiliations":[{"raw_affiliation_string":"Computer Science Department, Ruhr West University of Applied Sciences, L\u00fctzowstra\u00dfe 5, 46236 Bottrop, Germany","institution_ids":["https://openalex.org/I4210123225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078414923","display_name":"Uwe Handmann","orcid":"https://orcid.org/0000-0003-1230-9446"},"institutions":[{"id":"https://openalex.org/I4210123225","display_name":"Ruhr West University of Applied Sciences","ror":"https://ror.org/02nkxrq89","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210123225"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Uwe Handmann","raw_affiliation_strings":["Computer Science Department, Ruhr West University of Applied Sciences, L\u00fctzowstra\u00dfe 5, 46236 Bottrop, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1230-9446","affiliations":[{"raw_affiliation_string":"Computer Science Department, Ruhr West University of Applied Sciences, L\u00fctzowstra\u00dfe 5, 46236 Bottrop, Germany","institution_ids":["https://openalex.org/I4210123225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032719063","https://openalex.org/A5044579966"],"corresponding_institution_ids":["https://openalex.org/I4210123225"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.6221,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85516863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"6","issue":"4","first_page":"2783","last_page":"2807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9919999837875366,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9879000186920166,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.820252537727356},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.6814676523208618},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6334398984909058},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6054958701133728},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.599122166633606},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.595025897026062},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.530525803565979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.530471920967102},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49294590950012207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820252537727356},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.6814676523208618},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6334398984909058},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6054958701133728},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.599122166633606},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.595025897026062},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.530525803565979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.530471920967102},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49294590950012207},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/make6040133","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make6040133","pdf_url":"https://www.mdpi.com/2504-4990/6/4/133/pdf?version=1733145003","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a137ee7ca1954911a1949d7988d2c34d","is_oa":true,"landing_page_url":"https://doaj.org/article/a137ee7ca1954911a1949d7988d2c34d","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":"Machine Learning and Knowledge Extraction, Vol 6, Iss 4, Pp 2783-2807 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/make6040133","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make6040133","pdf_url":"https://www.mdpi.com/2504-4990/6/4/133/pdf?version=1733145003","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405072733.pdf","grobid_xml":"https://content.openalex.org/works/W4405072733.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2340897893","https://openalex.org/W2565639579","https://openalex.org/W2970925270","https://openalex.org/W3092462694","https://openalex.org/W3135367836","https://openalex.org/W3138516171","https://openalex.org/W3159481202","https://openalex.org/W3174770825","https://openalex.org/W3180659539","https://openalex.org/W3188582951","https://openalex.org/W3205203171","https://openalex.org/W4205991051","https://openalex.org/W4312439332","https://openalex.org/W4312655391","https://openalex.org/W4312815172","https://openalex.org/W4385573610","https://openalex.org/W4386071535","https://openalex.org/W4386071839","https://openalex.org/W4386790226","https://openalex.org/W4387169919","https://openalex.org/W4389086678","https://openalex.org/W4389195072","https://openalex.org/W4390190100","https://openalex.org/W4390873343","https://openalex.org/W4390874575","https://openalex.org/W4392579942","https://openalex.org/W4401886421","https://openalex.org/W4402616209","https://openalex.org/W4402916137","https://openalex.org/W4404844643","https://openalex.org/W6687483927","https://openalex.org/W6759579507","https://openalex.org/W6796581206","https://openalex.org/W6810859482","https://openalex.org/W6838393215","https://openalex.org/W6851607685","https://openalex.org/W6853251322"],"related_works":["https://openalex.org/W3171293857","https://openalex.org/W4388032146","https://openalex.org/W4308023773","https://openalex.org/W4386815496","https://openalex.org/W4384345669","https://openalex.org/W4361231003","https://openalex.org/W4360603156","https://openalex.org/W3215620590","https://openalex.org/W4287812764","https://openalex.org/W4385567133"],"abstract_inverted_index":{"Research":[0],"and":[1,69,86,133,146,167,188],"applications":[2],"in":[3,27,47,114,147],"artificial":[4],"intelligence":[5],"have":[6],"recently":[7],"shifted":[8],"with":[9],"the":[10,24,48,62,94,111,157,171,180],"rise":[11],"of":[12,50,64,104,131,159,173,182],"large":[13],"pretrained":[14],"models,":[15],"which":[16],"deliver":[17],"state-of-the-art":[18],"results":[19,154],"across":[20,77],"numerous":[21],"tasks.":[22,196],"However,":[23],"substantial":[25],"increase":[26],"parameters":[28],"introduces":[29],"a":[30,107],"need":[31],"for":[32,53,93,193],"parameter-efficient":[33,43],"training":[34],"strategies.":[35],"Despite":[36],"significant":[37],"advancements,":[38],"limited":[39],"research":[40],"has":[41],"explored":[42],"fine-tuning":[44,100],"(PEFT)":[45],"methods":[46],"context":[49],"transformer-based":[51],"models":[52,76],"instance":[54,194],"segmentation.":[55],"Addressing":[56],"this":[57,59,177],"gap,":[58],"study":[60],"investigates":[61],"effectiveness":[63],"PEFT":[65,160,183],"methods,":[66],"specifically":[67],"adapters":[68,123],"Low-Rank":[70],"Adaptation":[71],"(LoRA),":[72],"applied":[73,142],"to":[74,89,143,184],"two":[75],"four":[78],"benchmark":[79],"datasets.":[80],"Integrating":[81],"sequentially":[82],"arranged":[83],"adapter":[84,151],"modules":[85],"applying":[87],"LoRA":[88],"deformable":[90,144],"attention\u2014explored":[91],"here":[92],"first":[95],"time\u2014achieves":[96],"competitive":[97],"performance":[98,132],"while":[99],"only":[101],"about":[102],"1\u20136%":[103],"model":[105,168],"parameters,":[106],"marked":[108],"improvement":[109],"over":[110],"40\u201355%":[112],"required":[113],"traditional":[115],"fine-tuning.":[116],"Key":[117],"findings":[118],"indicate":[119],"that":[120,156],"using":[121],"2\u20133":[122],"per":[124],"transformer":[125],"block":[126],"offers":[127],"an":[128],"optimal":[129],"balance":[130],"efficiency.":[134],"Furthermore,":[135],"LoRA,":[136],"exhibits":[137],"strong":[138],"parameter":[139],"efficiency":[140],"when":[141],"attention,":[145],"certain":[148],"cases":[149],"surpasses":[150],"configurations.":[152],"These":[153],"show":[155],"impact":[158],"techniques":[161],"varies":[162],"based":[163],"on":[164],"dataset":[165],"complexity":[166],"architecture,":[169],"underscoring":[170],"importance":[172],"context-specific":[174],"tuning.":[175],"Overall,":[176],"work":[178],"demonstrates":[179],"potential":[181],"enable":[185],"scalable,":[186],"customizable,":[187],"computationally":[189],"efficient":[190],"transfer":[191],"learning":[192],"segmentation":[195]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}