{"id":"https://openalex.org/W4414801982","doi":"https://doi.org/10.1109/iccv51701.2025.01896","title":"ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction","display_name":"ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414801982","doi":"https://doi.org/10.1109/iccv51701.2025.01896"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.08678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Juan Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juan Yeo","raw_affiliation_strings":["Gradudate School of Data Science, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gradudate School of Data Science, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032680380","display_name":"Soonwoo Cha","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soonwoo Cha","raw_affiliation_strings":["Gradudate School of Data Science, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gradudate School of Data Science, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiwoo Song","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiwoo Song","raw_affiliation_strings":["Gradudate School of Data Science, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gradudate School of Data Science, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyunbin Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunbin Jin","raw_affiliation_strings":["Gradudate School of Data Science, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gradudate School of Data Science, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065728469","display_name":"Taesup Kim","orcid":"https://orcid.org/0000-0002-8357-1700"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taesup Kim","raw_affiliation_strings":["Gradudate School of Data Science, Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gradudate School of Data Science, Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.12763558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20390","last_page":"20400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9891999959945679,"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/T13629","display_name":"Text Readability and Simplification","score":0.9854000210762024,"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/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6845999956130981},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5534999966621399},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5056999921798706},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4887000024318695},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.44440001249313354},{"id":"https://openalex.org/keywords/sharpening","display_name":"Sharpening","score":0.40779998898506165},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3928000032901764},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.3869999945163727},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36890000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706999778747559},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6845999956130981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6414999961853027},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5534999966621399},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5056999921798706},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4887000024318695},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C2781137444","wikidata":"https://www.wikidata.org/wiki/Q237105","display_name":"Sharpening","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3903000056743622},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35089999437332153},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2759000062942505},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2619999945163727}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.08678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08678","pdf_url":"https://arxiv.org/pdf/2506.08678","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.08678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.08678","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.08678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08678","pdf_url":"https://arxiv.org/pdf/2506.08678","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7802052495","display_name":null,"funder_award_id":"RS-2024-00345809","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"such":[2],"as":[3],"CLIP":[4,23,124,151],"have":[5],"recently":[6],"propelled":[7],"open-vocabulary":[8,137,175],"dense":[9,35,176],"prediction":[10,36],"tasks":[11],"by":[12,96],"enabling":[13],"recognition":[14],"of":[15,19,64,100,123,158,165],"a":[16,85,101],"broad":[17],"range":[18],"visual":[20],"concepts.":[21],"However,":[22],"still":[24],"struggles":[25],"with":[26],"fine-grained,":[27],"region-level":[28],"understanding,":[29],"hindering":[30],"its":[31],"effectiveness":[32,157],"on":[33,70],"these":[34,78],"tasks.":[37],"We":[38],"identify":[39],"two":[40],"pivotal":[41],"factors":[42],"required":[43],"to":[44,120],"address":[45],"this":[46],"limitation:":[47],"semantic":[48,65,91,129,141,168],"coherence":[49,92,169],"and":[50,67,93,115,140,161,170],"fine-grained":[51,59,94,171],"vision-language":[52],"alignment.":[53],"Current":[54],"adaptation":[55],"methods":[56],"often":[57,68],"improve":[58],"alignment":[60,95,172],"at":[61],"the":[62,156,163],"expense":[63],"coherence,":[66],"rely":[69],"extra":[71],"modules":[72],"or":[73],"supervised":[74],"fine-tuning.":[75],"To":[76],"overcome":[77],"issues,":[79],"we":[80],"propose":[81],"Any-to-Any":[82],"Self-Distillation":[83],"(ATAS),":[84],"novel":[86],"approach":[87,160],"that":[88],"simultaneously":[89],"enhances":[90],"leveraging":[97],"own":[98],"knowledge":[99],"model":[102],"across":[103],"all":[104],"representation":[105],"levels.":[106],"Unlike":[107],"prior":[108],"methods,":[109],"ATAS":[110,144],"uses":[111],"only":[112],"unlabeled":[113],"images":[114],"an":[116],"internal":[117],"self-distillation":[118],"process":[119],"refine":[121],"representations":[122],"vision":[125],"encoders,":[126],"preserving":[127],"local":[128,133],"consistency":[130],"while":[131],"sharpening":[132],"detail":[134],"recognition.":[135],"On":[136],"object":[138],"detection":[139],"segmentation":[142],"benchmarks,":[143],"achieves":[145],"substantial":[146],"performance":[147],"gains,":[148],"outperforming":[149],"baseline":[150],"models.":[152],"These":[153],"results":[154],"validate":[155],"our":[159],"underscore":[162],"importance":[164],"jointly":[166],"maintaining":[167],"for":[173],"advanced":[174],"prediction.":[177]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}