{"id":"https://openalex.org/W4414929907","doi":"https://doi.org/10.1109/wacv61042.2026.00104","title":"Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training Improves Dense Prediction","display_name":"Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training Improves Dense Prediction","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4414929907","doi":"https://doi.org/10.1109/wacv61042.2026.00104"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00104","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/2503.17526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092529483","display_name":"S\u00e9bastien Quetin","orcid":"https://orcid.org/0009-0005-5391-7319"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"S\u00e9bastien Quetin","raw_affiliation_strings":["McGill University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029743023","display_name":"Tapotosh Ghosh","orcid":"https://orcid.org/0000-0001-5228-666X"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tapotosh Ghosh","raw_affiliation_strings":["University of Calgary,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Calgary,Canada","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033210702","display_name":"Farhad Maleki","orcid":"https://orcid.org/0000-0002-5673-8210"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Farhad Maleki","raw_affiliation_strings":["University of Calgary,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Calgary,Canada","institution_ids":["https://openalex.org/I168635309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01042362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1000","last_page":"1010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7991999983787537,"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/T10320","display_name":"Neural Networks and Applications","score":0.7991999983787537,"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/segmentation","display_name":"Segmentation","score":0.7411999702453613},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6359000205993652},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.6158999800682068},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5968000292778015},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44850000739097595},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.444599986076355},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4381999969482422},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4049000144004822}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7411999702453613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190999984741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6638000011444092},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6359000205993652},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.6158999800682068},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4381999969482422},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4049000144004822},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3296000063419342},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2556000053882599},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.2515000104904175},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00104","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:2503.17526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17526","pdf_url":"https://arxiv.org/pdf/2503.17526","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.17526","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.17526","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":"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:2503.17526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.17526","pdf_url":"https://arxiv.org/pdf/2503.17526","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310537","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320325651","display_name":"Alberta Innovates","ror":null},{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414929907.pdf","grobid_xml":"https://content.openalex.org/works/W4414929907.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Contrastive":[0],"learning":[1,50],"methods":[2],"in":[3,182],"self-supervised":[4,49],"settings":[5],"have":[6],"primarily":[7],"focused":[8],"on":[9,106,114,125,155,162],"pre-training":[10,35,88,121,191],"encoders,":[11],"while":[12],"decoders":[13,67],"are":[14],"typically":[15],"introduced":[16],"and":[17,38,68,117,133,144,148,158,172,177,180],"trained":[18],"separately":[19],"for":[20,98,196],"downstream":[21],"dense":[22,99,173,197],"prediction":[23],"tasks.":[24],"However,":[25],"this":[26,41],"conventional":[27],"approach":[28],"overlooks":[29],"the":[30,86,109,138],"potential":[31],"benefits":[32],"of":[33,89,108],"jointly":[34],"both":[36],"encoder":[37,124],"decoder.":[39],"In":[40],"paper,":[42],"we":[43,74],"propose":[44],"DeCon,":[45],"an":[46],"efficient":[47],"encoder-decoder":[48,78,90],"(SSL)":[51],"framework":[52,97,140],"that":[53,189],"supports":[54],"joint":[55,87,190],"contrastive":[56,71,79,95],"pre-training.":[57],"We":[58],"first":[59],"extend":[60],"existing":[61],"SSL":[62,96],"architectures":[63],"to":[64,84,137],"accommodate":[65],"diverse":[66],"their":[69],"corresponding":[70],"losses.":[72],"Then,":[73],"introduce":[75],"a":[76,94,122],"weighted":[77],"loss":[80],"with":[81],"non-competing":[82],"objectives":[83],"enable":[85],"architectures.":[91],"By":[92],"adapting":[93],"prediction,":[100],"DeCon":[101,128],"establishes":[102],"consistent":[103],"state-of-the-art":[104],"performance":[105],"most":[107],"evaluated":[110],"tasks":[111,174],"when":[112,120],"pre-trained":[113],"Imagenet-1K,":[115],"COCO":[116,126,130],"COCO+.":[118],"Notably,":[119],"ResNet-50":[123],"dataset,":[127],"improves":[129],"object":[131,178],"detection":[132],"instance":[134],"segmentation":[135,151,176],"compared":[136],"baseline":[139],"by":[141,152,159],"+0.37":[142],"AP":[143],"+0.32":[145],"AP,":[146],"respectively,":[147],"boosts":[149],"semantic":[150],"+1.42":[153],"mIoU":[154,161],"Pascal":[156],"VOC":[157],"+0.50":[160],"Cityscapes.":[163],"These":[164],"improvements":[165],"generalize":[166],"across":[167],"recent":[168],"backbones,":[169],"decoders,":[170],"datasets,":[171],"beyond":[175],"detection,":[179],"persist":[181],"out-of-domain":[183],"scenarios,":[184],"including":[185],"limited-data":[186],"settings,":[187],"demonstrating":[188],"significantly":[192],"enhances":[193],"representation":[194],"quality":[195],"prediction.":[198],"Code":[199],"is":[200],"available":[201],"at":[202],"https://github.com/sebquetin/DeCon.git.":[203]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}