{"id":"https://openalex.org/W7125801993","doi":"https://doi.org/10.1109/tpami.2026.3658114","title":"DFormer++: Improving RGBD Representation Learning for Semantic Segmentation","display_name":"DFormer++: Improving RGBD Representation Learning for Semantic Segmentation","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125801993","doi":"https://doi.org/10.1109/tpami.2026.3658114","pmid":"https://pubmed.ncbi.nlm.nih.gov/41591861"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3658114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3658114","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123992736","display_name":"Bo-Wen Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo-Wen Yin","raw_affiliation_strings":["VCIP, School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0000-9988-3509","affiliations":[{"raw_affiliation_string":"VCIP, School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123926952","display_name":"Jiao-Long Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiao-Long Cao","raw_affiliation_strings":["VCIP, School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123988699","display_name":"Dan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dan Xu","raw_affiliation_strings":["Hong Kong University of Science and Technology (HKUST), Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-0136-9603","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (HKUST), Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123947970","display_name":"Ming-Ming Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Ming Cheng","raw_affiliation_strings":["VCIP, School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5550-8758","affiliations":[{"raw_affiliation_string":"VCIP, School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123948518","display_name":"Qibin Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibin Hou","raw_affiliation_strings":["VCIP, School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8388-8708","affiliations":[{"raw_affiliation_string":"VCIP, School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.7937,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9873305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"48","issue":"7","first_page":"7195","last_page":"7208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9205999970436096,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9205999970436096,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.022299999371170998,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.007000000216066837,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.8070999979972839},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.722599983215332},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6848999857902527},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6759999990463257},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.59170001745224},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5218999981880188},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4803999960422516},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4117000102996826},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3849000036716461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8327000141143799},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.8070999979972839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7452999949455261},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.722599983215332},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6848999857902527},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6759999990463257},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.59170001745224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5218999981880188},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4803999960422516},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.478300005197525},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4117000102996826},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.31360000371932983},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3125},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2026.3658114","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3658114","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41591861","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41591861","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169849","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169849","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2619946564","display_name":null,"funder_award_id":"070-63253220","funder_id":"https://openalex.org/F4320323021","funder_display_name":"Nankai University"},{"id":"https://openalex.org/G3149626323","display_name":null,"funder_award_id":"62276145","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3577359050","display_name":null,"funder_award_id":"62522607","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6540330966","display_name":null,"funder_award_id":"62495061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323021","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"explore":[1],"the":[2,8,14,49,58,63,73,78,114,118,141],"potential":[3],"of":[4,92,117],"pretrain-and-finetune":[5,28],"manner":[6],"on":[7,168],"RGB-D":[9,27,35,59,82,93,150,171],"semantic":[10,36,172],"segmentation":[11,173],"to":[12,30,57,80],"solve":[13],"common":[15],"mismatch":[16],"problem":[17],"in":[18,122,132],"this":[19],"field.":[20],"Specifically,":[21],"we":[22,61],"present":[23],"DFormer++,":[24],"a":[25,90,107],"novel":[26,108],"framework":[29],"learn":[31],"transferable":[32],"representations":[33],"for":[34,99,148],"segmentation.":[37],"This":[38],"paper":[39],"has":[40,136],"two":[41],"vital":[42],"innovations.":[43],"1)":[44],"Framework":[45],"perspective:":[46,86],"Different":[47],"from":[48,68],"existing":[50],"methods":[51],"that":[52,161],"finetune":[53],"RGB":[54,102,126],"pretrained":[55,127],"backbone":[56,64],"scenes,":[60],"pretrain":[62],"using":[65],"image-depth":[66],"pairs":[67],"ImageNet-1":[69],"K,":[70],"and":[71,103,152,155],"hence":[72],"model":[74,88],"is":[75],"endowed":[76],"with":[77],"capacity":[79],"encode":[81],"representations;":[83],"2)":[84],"Architecture":[85],"Our":[87,111],"comprises":[89],"sequence":[91],"attention":[94,109],"blocks,":[95],"which":[96,129],"are":[97],"tailored":[98,142],"encoding":[100,116,149],"both":[101],"depth":[104,123],"information":[105],"through":[106],"mechanism.":[110],"DFormer++":[112,163],"avoids":[113],"mismatched":[115],"3D":[119],"geometry":[120],"relationships":[121],"maps":[124],"by":[125],"backbones,":[128],"widely":[130],"lies":[131],"previous":[133],"works":[134],"but":[135],"not":[137],"been":[138],"resolved.":[139],"Meanwhile,":[140],"architecture":[143],"greatly":[144],"reduces":[145],"redundant":[146],"parameters":[147],"data":[151],"achieves":[153,164],"efficient":[154],"accurate":[156],"perception.":[157],"Experimental":[158],"results":[159],"show":[160],"our":[162],"new":[165],"cutting-edge":[166],"performance":[167],"three":[169],"popular":[170],"benchmarks.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-06T06:22:57.294733","created_date":"2026-01-28T00:00:00"}