{"id":"https://openalex.org/W7143289174","doi":"https://doi.org/10.48550/arxiv.2603.26258","title":"ARTA: Adaptive Mixed-Resolution Token Allocation for Efficient Dense Feature Extraction","display_name":"ARTA: Adaptive Mixed-Resolution Token Allocation for Efficient Dense Feature Extraction","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7143289174","doi":"https://doi.org/10.48550/arxiv.2603.26258"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.26258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26258","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.26258","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072202591","display_name":"David Hagerman","orcid":"https://orcid.org/0000-0002-5193-3789"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hagerman, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054318217","display_name":"Roman Naeem","orcid":"https://orcid.org/0009-0001-2625-125X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naeem, Roman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111142522","display_name":"Erik Brorsson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brorsson, Erik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130996104","display_name":"Fredrik Kahl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kahl, Fredrik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029413988","display_name":"Lennart Svensson","orcid":"https://orcid.org/0000-0003-0206-9186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Svensson, Lennart","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":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/T10036","display_name":"Advanced Neural Network Applications","score":0.7731000185012817,"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":0.7731000185012817,"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":0.0608999989926815,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04529999941587448,"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/allocator","display_name":"Allocator","score":0.5917999744415283},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5752000212669373},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5123999714851379},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4481000006198883},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44679999351501465},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.4293999969959259},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42010000348091125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795799970626831},{"id":"https://openalex.org/C162262903","wikidata":"https://www.wikidata.org/wiki/Q343527","display_name":"Allocator","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5752000212669373},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5123999714851379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4537999927997589},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37720000743865967},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3343999981880188},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25589999556541443},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.26258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26258","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.26258","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26258","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.8181803226470947,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"ARTA,":[2],"a":[3,30,45,57,80,86],"mixed-resolution":[4],"coarse-to-fine":[5],"vision":[6],"transformer":[7],"for":[8],"efficient":[9],"dense":[10,18],"feature":[11],"extraction.":[12],"Unlike":[13],"models":[14],"that":[15,114],"begin":[16],"with":[17,24,123],"high-resolution":[19],"(fine)":[20],"tokens,":[21,98],"ARTA":[22,115],"starts":[23],"low-resolution":[25],"(coarse)":[26],"tokens":[27,53,77],"and":[28,50,96,121,127,153],"uses":[29],"lightweight":[31],"allocator":[32,42],"to":[33,54,69,78],"predict":[34],"which":[35],"regions":[36],"require":[37],"more":[38],"fine":[39,97],"tokens.":[40],"The":[41],"iteratively":[43],"predicts":[44],"semantic":[46,82],"(class)":[47],"boundary":[48,71],"score":[49],"allocates":[51],"additional":[52],"patches":[55],"above":[56],"low":[58],"threshold,":[59],"concentrating":[60],"token":[61],"density":[62],"near":[63],"boundaries":[64],"while":[65,105,149],"maintaining":[66],"high":[67],"sensitivity":[68],"weak":[70],"evidence.":[72],"This":[73],"targeted":[74],"allocation":[75],"encourages":[76],"represent":[79],"single":[81],"class":[83,148],"rather":[84],"than":[85,156],"mixture":[87],"of":[88],"classes.":[89],"Mixed-resolution":[90],"attention":[91],"enables":[92],"interaction":[93],"between":[94],"coarse":[95],"focusing":[99],"computation":[100],"on":[101,119,131,143],"semantically":[102],"complex":[103],"areas":[104],"avoiding":[106],"redundant":[107],"processing":[108],"in":[109,145],"homogeneous":[110],"regions.":[111],"Experiments":[112],"demonstrate":[113],"achieves":[116],"state-of-the-art":[117],"results":[118],"ADE20K":[120,144],"COCO-Stuff":[122],"substantially":[124],"fewer":[125,151],"FLOPs,":[126],"delivers":[128],"competitive":[129],"performance":[130],"Cityscapes":[132],"at":[133],"markedly":[134],"lower":[135],"compute.":[136],"For":[137],"example,":[138],"ARTA-Base":[139],"attains":[140],"54.6":[141],"mIoU":[142],"the":[146],"~100M-parameter":[147],"using":[150],"FLOPs":[152],"less":[154],"memory":[155],"comparable":[157],"backbones.":[158]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-31T00:00:00"}