{"id":"https://openalex.org/W4415286445","doi":"https://doi.org/10.1109/wacv61042.2026.00080","title":"Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis","display_name":"Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4415286445","doi":"https://doi.org/10.1109/wacv61042.2026.00080"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/2503.15060","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034276221","display_name":"Imanol G. Estepa","orcid":"https://orcid.org/0000-0001-6478-9547"},"institutions":[{"id":"https://openalex.org/I71999127","display_name":"Universitat de Barcelona","ror":"https://ror.org/021018s57","country_code":"ES","type":"education","lineage":["https://openalex.org/I71999127"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Imanol G. Estepa","raw_affiliation_strings":["Universitat de Barcelona,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat de Barcelona,Barcelona,Spain","institution_ids":["https://openalex.org/I71999127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016451099","display_name":"Jes\u00fas M. Rodr\u00edguez-de-Vera","orcid":"https://orcid.org/0000-0003-1412-8972"},"institutions":[{"id":"https://openalex.org/I71999127","display_name":"Universitat de Barcelona","ror":"https://ror.org/021018s57","country_code":"ES","type":"education","lineage":["https://openalex.org/I71999127"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jes\u00fas M. Rodr\u00edguez-de-Vera","raw_affiliation_strings":["Universitat de Barcelona,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat de Barcelona,Barcelona,Spain","institution_ids":["https://openalex.org/I71999127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028019174","display_name":"Ignacio Saras\u00faa","orcid":"https://orcid.org/0000-0002-1074-3903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ignacio Saras\u00faa","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080818948","display_name":"Bhalaji Nagarajan","orcid":"https://orcid.org/0000-0003-2473-2057"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Bhalaji Nagarajan","raw_affiliation_strings":["Barcelona Supercomputing Center,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center,Barcelona,Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083867344","display_name":"Petia Radeva","orcid":"https://orcid.org/0000-0003-0047-5172"},"institutions":[{"id":"https://openalex.org/I71999127","display_name":"Universitat de Barcelona","ror":"https://ror.org/021018s57","country_code":"ES","type":"education","lineage":["https://openalex.org/I71999127"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Petia Radeva","raw_affiliation_strings":["Universitat de Barcelona,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat de Barcelona,Barcelona,Spain","institution_ids":["https://openalex.org/I71999127"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.01217769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"751","last_page":"761"},"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":0.9842000007629395,"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":0.9842000007629395,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9842000007629395,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.984000027179718,"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/security-token","display_name":"Security token","score":0.6590999960899353},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5687999725341797},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5389999747276306},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.5160999894142151},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4424000084400177},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41690000891685486},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.39079999923706055},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.37549999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878000140190125},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6590999960899353},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5687999725341797},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5192000269889832},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3882000148296356},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.37549999356269836},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.36570000648498535},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31049999594688416},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.15060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.15060","pdf_url":"https://arxiv.org/pdf/2503.15060","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.15060","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.15060","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.15060","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.15060","pdf_url":"https://arxiv.org/pdf/2503.15060","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":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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"representation":[1],"learning":[2],"and":[3,86,167,177,193,204],"generative":[4,82],"modeling":[5],"seek":[6],"to":[7,24,121,145],"understand":[8],"visual":[9],"data,":[10],"unifying":[11],"both":[12,29],"domains":[13],"remains":[14],"unexplored.":[15],"Recent":[16],"Unified":[17,68,159,207],"Self-Supervised":[18],"Learning":[19],"(SSL)":[20],"methods":[21],"have":[22],"started":[23],"bridge":[25],"the":[26,81,88,107,112,128,139,157],"gap":[27],"between":[28],"paradigms.":[30],"However,":[31],"they":[32],"either":[33],"extract":[34],"information":[35],"from":[36],"discriminative":[37],"pretrained":[38],"models":[39],"or":[40,94],"rely":[41],"solely":[42],"on":[43,124,151,169],"semantic":[44,108],"token":[45,109,146],"reconstruction,":[46],"which":[47],"requires":[48],"an":[49,131],"external":[50],"tokenizer":[51,133],"during":[52,96,134],"training":[53],"\u2014":[54],"introducing":[55],"a":[56,66,72,185],"significant":[57,202],"computational":[58,140],"overhead.":[59],"In":[60],"this":[61],"work,":[62],"we":[63],"introduce":[64],"Sorcen,":[65],"novel":[67,77],"SSL":[69,160,208],"framework,":[70],"incorporating":[71],"synergic":[73],"Contrastive-Reconstruction":[74],"objective.":[75,114],"Our":[76],"Contrastive":[78],"objective,":[79],"leverages":[80],"capabilities":[83],"of":[84],"Sorcen":[85,98,120,136,155,182],"eliminates":[87],"need":[89,129],"for":[90,130],"additional":[91],"image":[92,173,199],"crops":[93],"augmentations":[95],"training.":[97,135],"\"generates\"":[99],"contrastive":[100],"positive":[101],"samples,":[102],"called":[103],"Echoes,":[104],"directly":[105],"in":[106,190,197,206],"space":[110],"using":[111],"reconstruction":[113,147],"This":[115],"on-the-fly":[116],"Echo":[117],"generation,":[118,174,200],"enables":[119],"operate":[122],"exclusively":[123],"precomputed":[125],"tokens,":[126],"eliminating":[127],"online":[132],"significantly":[137],"reduces":[138],"overhead":[141],"by":[142,162],"60.8%":[143],"compared":[144],"SoTA.":[148],"Extensive":[149],"experiments":[150],"ImageNet-1k":[152],"demonstrate":[153],"that":[154],"outperforms":[156],"previous":[158],"SoTA":[161,189,195],"0.4%,":[163],"1.48":[164],"FID,":[165],"1.76%,":[166],"1.53%":[168],"linear":[170,191],"probing,":[171],"unconditional":[172,198],"few-shot":[175],"learning,":[176,179],"transfer":[178],"respectively.":[180],"Additionally,":[181],"establishes":[183],"as":[184],"new":[186],"single-crop":[187],"MIM":[188],"probing":[192],"achieves":[194],"performance":[196],"highlighting":[201],"improvements":[203],"breakthroughs":[205],"models1.":[209]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-17T00:00:00"}