{"id":"https://openalex.org/W4416063923","doi":"https://doi.org/10.1109/iccv51701.2025.00406","title":"DIP: Unsupervised Dense In-Context Post-Training of Visual Representations","display_name":"DIP: Unsupervised Dense In-Context Post-Training of Visual Representations","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416063923","doi":"https://doi.org/10.1109/iccv51701.2025.00406"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00406","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.18463","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095848610","display_name":"Sophia Sirko-Galouchenko","orcid":null},"institutions":[{"id":"https://openalex.org/I220619192","display_name":"Valeo (France)","ror":"https://ror.org/04ryqpf83","country_code":"FR","type":"company","lineage":["https://openalex.org/I220619192"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sophia Sirko-Galouchenko","raw_affiliation_strings":["Valeo.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Valeo.ai","institution_ids":["https://openalex.org/I220619192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070809773","display_name":"Spyros Gidaris","orcid":"https://orcid.org/0000-0003-1515-3635"},"institutions":[{"id":"https://openalex.org/I220619192","display_name":"Valeo (France)","ror":"https://ror.org/04ryqpf83","country_code":"FR","type":"company","lineage":["https://openalex.org/I220619192"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Spyros Gidaris","raw_affiliation_strings":["Valeo.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Valeo.ai","institution_ids":["https://openalex.org/I220619192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017371568","display_name":"Anton\u00edn Vobeck\u00fd","orcid":"https://orcid.org/0000-0001-8946-2057"},"institutions":[{"id":"https://openalex.org/I220619192","display_name":"Valeo (France)","ror":"https://ror.org/04ryqpf83","country_code":"FR","type":"company","lineage":["https://openalex.org/I220619192"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antonin Vobecky","raw_affiliation_strings":["Valeo.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Valeo.ai","institution_ids":["https://openalex.org/I220619192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003783466","display_name":"Andrei Bursuc","orcid":"https://orcid.org/0000-0003-2485-9402"},"institutions":[{"id":"https://openalex.org/I220619192","display_name":"Valeo (France)","ror":"https://ror.org/04ryqpf83","country_code":"FR","type":"company","lineage":["https://openalex.org/I220619192"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Andrei Bursuc","raw_affiliation_strings":["Valeo.ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Valeo.ai","institution_ids":["https://openalex.org/I220619192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017490804","display_name":"Nicolas Thome","orcid":"https://orcid.org/0000-0003-4871-3045"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I51101395","display_name":"Universit\u00e9 Paris 1 Panth\u00e9on-Sorbonne","ror":"https://ror.org/002t25c44","country_code":"FR","type":"education","lineage":["https://openalex.org/I51101395"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Thome","raw_affiliation_strings":["Sorbonne Université, CNRS, ISIR,Paris,France,F-75005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Université, CNRS, ISIR,Paris,France,F-75005","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I51101395","https://openalex.org/I1294671590"]}]}],"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":0.2925293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4264","last_page":"4274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.42820000648498535,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.42820000648498535,"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":0.1632000058889389,"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/T11448","display_name":"Face recognition and analysis","score":0.07569999992847443,"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/encoder","display_name":"Encoder","score":0.7745000123977661},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5259000062942505},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5130000114440918},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5040000081062317},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4700999855995178},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.46959999203681946},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39399999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7865999937057495},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7745000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7141000032424927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5299000144004822},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5259000062942505},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4700999855995178},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2578999996185303}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.00406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00406","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:2506.18463","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.18463","pdf_url":"https://arxiv.org/pdf/2506.18463","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":"pmh:oai:HAL:hal-05507571v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05507571","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"ICCV 2025, 2025","raw_type":"Journal articles"},{"id":"doi:10.48550/arxiv.2506.18463","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.18463","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:2506.18463","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.18463","pdf_url":"https://arxiv.org/pdf/2506.18463","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"DIP,":[2],"a":[3,67,89,106,127],"novel":[4],"unsupervised":[5],"post-training":[6,52],"method":[7,33],"designed":[8],"to":[9],"enhance":[10],"dense":[11,95,134],"image":[12],"representations":[13,96],"in":[14],"large-scale":[15],"pretrained":[16,68],"vision":[17,36,73,121],"encoders":[18],"for":[19,61,132],"in-context":[20,44,63,99,112],"scene":[21,113],"understanding.":[22],"Unlike":[23],"prior":[24,124],"approaches":[25],"that":[26,40,65],"rely":[27],"on":[28,53,88],"complex":[29],"self-distillation":[30],"architectures,":[31],"our":[32],"trains":[34],"the":[35,72,119],"encoder":[37,74,122],"using":[38],"pseudo-tasks":[39],"explicitly":[41],"simulate":[42],"downstream":[43,110],"scenarios,":[45],"inspired":[46],"by":[47],"meta-learning":[48],"principles.":[49],"To":[50],"enable":[51],"unlabeled":[54],"data,":[55],"we":[56],"propose":[57],"an":[58],"automatic":[59],"mechanism":[60],"generating":[62],"tasks":[64],"combines":[66],"diffusion":[69],"model":[70],"and":[71,80,123,129],"itself.":[75],"DIP":[76],"is":[77],"simple,":[78],"unsupervised,":[79],"computationally":[81],"efficient,":[82],"requiring":[83],"less":[84],"than":[85],"9":[86],"hours":[87],"single":[90],"A100":[91],"GPU.":[92],"By":[93],"learning":[94],"through":[97],"pseudo":[98],"tasks,":[100],"it":[101],"achieves":[102],"strong":[103],"performance":[104],"across":[105],"wide":[107],"variety":[108],"of":[109],"real-world":[111],"understanding":[114],"tasks.":[115],"It":[116],"outperforms":[117],"both":[118],"initial":[120],"methods,":[125],"offering":[126],"practical":[128],"effective":[130],"solution":[131],"improving":[133],"representations.":[135],"Code":[136],"available":[137],"here:":[138],"https://github.com/sirkosophia/DIP":[139]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}