{"id":"https://openalex.org/W4417231739","doi":"https://doi.org/10.1109/iccv51701.2025.00042","title":"Scaling Language-Free Visual Representation Learning","display_name":"Scaling Language-Free Visual Representation Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417231739","doi":"https://doi.org/10.1109/iccv51701.2025.00042"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00042","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.01017","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101809215","display_name":"David D. Fan","orcid":"https://orcid.org/0000-0002-8261-1045"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Fan","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055545928","display_name":"Shengbang Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengbang Tong","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009199938","display_name":"Jiachen Zhu","orcid":"https://orcid.org/0000-0003-1325-3552"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiachen Zhu","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109576489","display_name":"Koustuv Sinha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koustuv Sinha","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452097","display_name":"Zhuang Liu","orcid":"https://orcid.org/0000-0002-4269-8297"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang Liu","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101507596","display_name":"Xinlei Chen","orcid":"https://orcid.org/0000-0001-5233-8335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinlei Chen","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089819604","display_name":"Michael Rabbat","orcid":"https://orcid.org/0000-0003-0536-7904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Rabbat","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057065873","display_name":"Nicolas Ballas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Ballas","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001226970","display_name":"Yann LeCun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yann LeCun","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040676689","display_name":"Amir Bar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amir Bar","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035866142","display_name":"Sheng Quan Xie","orcid":"https://orcid.org/0000-0003-2641-2620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saining Xie","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9538000226020813,"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":0.9538000226020813,"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":0.025200000032782555,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.007499999832361937,"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/semantics","display_name":"Semantics (computer science)","score":0.6050000190734863},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46939998865127563},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4499000012874603},{"id":"https://openalex.org/keywords/visual-learning","display_name":"Visual learning","score":0.39410001039505005},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.3865000009536743},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.33469998836517334},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.3292999863624573},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.32409998774528503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728600025177002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6241999864578247},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6050000190734863},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46939998865127563},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3865000009536743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3797000050544739},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C164280684","wikidata":"https://www.wikidata.org/wiki/Q5529040","display_name":"Gaze-contingency paradigm","level":4,"score":0.3116999864578247},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.28380000591278076},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2628999948501587}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00042","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:2504.01017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.01017","pdf_url":"https://arxiv.org/pdf/2504.01017","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.01017","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.01017","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.01017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.01017","pdf_url":"https://arxiv.org/pdf/2504.01017","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1597987600","display_name":null,"funder_award_id":"IIS2443404","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0,15],"Self-Supervised":[1],"Learning":[2],"(SSL)":[3],"currently":[4],"underperforms":[5],"Contrastive":[6],"Language-Image":[7],"Pretraining":[8],"(CLIP)":[9],"in":[10,68,111],"multimodal":[11,20],"settings":[12],"such":[13],"as":[14,92],"Question":[16],"Answering":[17],"(VQA).":[18],"This":[19],"gap":[21],"is":[22],"often":[23,40],"attributed":[24],"to":[25,60,129],"the":[26,50,61,69,85],"semantics":[27],"introduced":[28],"by":[29,76],"language":[30,64],"supervision,":[31,65],"even":[32,125],"though":[33],"visual":[34,53,79,103,119,135,156,161],"SSL":[35,80,104,120,136,157],"and":[36,81,89,115,118,147],"CLIP":[37,58,82,109],"models":[38,83,105,110],"are":[39],"trained":[41],"on":[42,84,141],"different":[43],"data.":[44],"In":[45,99],"this":[46,74,100],"work,":[47],"we":[48,133],"ask":[49],"question:":[51],"\"Do":[52],"self-supervised":[54],"approaches":[55],"lag":[56],"behind":[57],"due":[59],"lack":[62],"of":[63,113,145],"or":[66],"differences":[67],"training":[70,77],"data?\"":[71],"We":[72],"study":[73],"question":[75],"both":[78],"same":[86],"MetaCLIP":[87],"data,":[88],"leveraging":[90],"VQA":[91,146],"a":[93,142],"diverse":[94],"testbed":[95],"for":[96,168],"vision":[97,149],"encoders.":[98],"controlled":[101],"setup,":[102],"scale":[106],"better":[107],"than":[108],"terms":[112],"data":[114],"model":[116],"capacity,":[117],"performance":[121,140],"does":[122],"not":[123],"saturate":[124],"after":[126],"scaling":[127],"up":[128],"7B":[130],"parameters.":[131],"Consequently,":[132],"observe":[134],"methods":[137],"achieve":[138],"CLIP-level":[139],"wide":[143],"range":[144],"classic":[148],"benchmarks.":[150],"These":[151],"findings":[152],"demonstrate":[153],"that":[154],"pure":[155],"can":[158],"match":[159],"language-supervised":[160],"pretraining":[162],"at":[163],"scale,":[164],"opening":[165],"new":[166],"opportunities":[167],"vision-centric":[169],"representation":[170],"learning.":[171]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}