{"id":"https://openalex.org/W7129241298","doi":"https://doi.org/10.48550/arxiv.2602.13889","title":"Parameter-Efficient Fine-Tuning of DINOv2 for Large-Scale Font Classification","display_name":"Parameter-Efficient Fine-Tuning of DINOv2 for Large-Scale Font Classification","publication_year":2026,"publication_date":"2026-02-14","ids":{"openalex":"https://openalex.org/W7129241298","doi":"https://doi.org/10.48550/arxiv.2602.13889"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.13889","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126228158","display_name":"Daniel Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126248369","display_name":"Zaria Zinn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zinn, Zaria","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126203006","display_name":"Marcus Lowe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lowe, Marcus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18683832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.6998000144958496,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.6998000144958496,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07410000264644623,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.04439999908208847,"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/font","display_name":"Font","score":0.8284000158309937},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6513000130653381},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5788000226020813},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5331000089645386},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5001000165939331},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.40400001406669617},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35760000348091125}],"concepts":[{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.8284000158309937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577000260353088},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6513000130653381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6502000093460083},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5788000226020813},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5331000089645386},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.40400001406669617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3009999990463257},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C80797182","wikidata":"https://www.wikidata.org/wiki/Q17451","display_name":"Typeface","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.13889","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.13889","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.13889","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.13889","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.42363378405570984,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,58,96],"introduce":[1],"GoogleFontsBench,":[2],"the":[3,84,98,104],"first":[4],"public":[5],"benchmark":[6],"for":[7],"classifying":[8],"open-source":[9,109],"web":[10],"fonts,":[11],"addressing":[12],"a":[13,34,47,66],"gap":[14],"left":[15],"by":[16,55],"existing":[17],"benchmarks":[18],"that":[19,52],"cover":[20],"only":[21,81],"commercial":[22],"typefaces.":[23],"GoogleFontsBench":[24],"comprises":[25],"394":[26],"font":[27],"variants":[28],"across":[29],"32":[30],"Google":[31],"Fonts":[32],"families,":[33],"reproducible":[35],"synthetic":[36],"data":[37],"generation":[38],"pipeline":[39,107],"(~575":[40],"images":[41],"per":[42],"variant,":[43],"~226K":[44],"total),":[45],"and":[46,103],"typographically-grounded":[48],"evaluation":[49],"metric":[50],"(SWER)":[51],"weights":[53],"errors":[54,89],"visual":[56],"severity.":[57],"establish":[59],"baselines":[60],"using":[61],"six":[62],"fine-tuning":[63],"strategies":[64],"on":[65],"DINOv2":[67],"Vision":[68],"Transformer":[69],"backbone.":[70],"Parameter-efficient":[71],"adaptation":[72],"with":[73,88],"LoRA":[74],"achieves":[75],"99.0%":[76],"top-1":[77],"accuracy":[78],"while":[79],"training":[80,106],"1%":[82],"of":[83],"model's":[85],"87.2M":[86],"parameters,":[87],"140x":[90],"less":[91],"severe":[92],"than":[93],"random":[94],"guessing.":[95],"release":[97],"benchmark,":[99],"all":[100],"trained":[101],"models,":[102],"full":[105],"as":[108],"resources.":[110]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-02-18T00:00:00"}