{"id":"https://openalex.org/W7138387550","doi":"https://doi.org/10.1609/aaai.v40i7.37433","title":"Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization","display_name":"Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138387550","doi":"https://doi.org/10.1609/aaai.v40i7.37433"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i7.37433","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37433","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i7.37433","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129730736","display_name":"Yan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007736768","display_name":"Yongyi Su","orcid":"https://orcid.org/0009-0001-6911-8256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongyi Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129713246","display_name":"Xin Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129677548","display_name":"Le Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129711005","display_name":"Xun Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xun Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"7","first_page":"5185","last_page":"5193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.4284000098705292,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.4284000098705292,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.1915999948978424,"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":0.12610000371932983,"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/regularization","display_name":"Regularization (linguistics)","score":0.6686000227928162},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6654999852180481},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6133999824523926},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5740000009536743},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5633999705314636},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4643000066280365},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.45739999413490295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6711000204086304},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6686000227928162},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6654999852180481},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6133999824523926},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5717999935150146},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45350000262260437},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C2780267512","wikidata":"https://www.wikidata.org/wiki/Q6997828","display_name":"Nestedness","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i7.37433","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37433","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37433","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i7.37433","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37433","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1972214355","display_name":null,"funder_award_id":"M23L7b0021","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"},{"id":"https://openalex.org/G5628311552","display_name":null,"funder_award_id":"2023A1515110077","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,38,66,86,123,193],"foundation":[3,68],"models":[4,40,69],"has":[5],"substantially":[6],"advanced":[7],"zero-shot":[8],"generalization":[9,184],"in":[10,70,120],"monocular":[11],"depth":[12,126],"estimation":[13],"(MDE),":[14],"as":[15,82],"exemplified":[16],"by":[17],"the":[18,36,64,83,121,131,153,161],"Depth":[19],"Anything":[20],"series.":[21],"However,":[22],"given":[23],"access":[24],"to":[25,62,103,128,139,151],"some":[26],"data":[27],"from":[28],"downstream":[29],"tasks,":[30],"a":[31,50,78,116,145,190],"natural":[32],"question":[33],"arises:":[34],"can":[35],"performance":[37,188],"these":[39],"be":[41],"further":[42,90,129],"improved?":[43],"To":[44,89],"this":[45],"end,":[46],"we":[47,93,114],"propose":[48],"WeSTAR,":[49],"parameter-efficient":[51],"framework":[52],"that":[53,180],"performs":[54],"\\textbf{We}akly":[55],"supervised":[56],"\\textbf{S}elf-\\textbf{T}raining":[57],"\\textbf{A}daptation":[58],"with":[59],"\\textbf{R}egularization,":[60],"designed":[61],"enhance":[63],"robustness":[65],"MDE":[67],"unseen":[71],"and":[72,107,159,170,176,185],"diverse":[73,175],"domains.":[74],"We":[75],"first":[76],"adopt":[77],"dense":[79,112],"self-training":[80],"objective":[81],"primary":[84],"source":[85],"structural":[87,109],"self-supervision.":[88],"improve":[91],"robustness,":[92],"introduce":[94,115],"semantically-aware":[95],"hierarchical":[96],"normalization,":[97],"which":[98,134],"exploits":[99],"instance-level":[100],"segmentation":[101],"maps":[102],"perform":[104],"more":[105],"stable":[106],"multi-scale":[108],"normalization.":[110],"Beyond":[111],"supervision,":[113],"cost-efficient":[117],"weak":[118],"supervision":[119],"form":[122],"pairwise":[124],"ordinal":[125,137],"annotations":[127],"guide":[130],"adaptation":[132],"process,":[133],"enforces":[135],"informative":[136],"constraints":[138],"mitigate":[140],"local":[141],"topological":[142],"errors.":[143],"Finally,":[144],"weight":[146],"regularization":[147],"loss":[148],"is":[149],"employed":[150],"anchor":[152],"LoRA":[154],"updates,":[155],"ensuring":[156],"training":[157],"stability":[158],"preserving":[160],"model's":[162],"generalizable":[163],"knowledge.":[164],"Extensive":[165],"experiments":[166],"on":[167],"both":[168],"realistic":[169],"corrupted":[171],"out-of-distribution":[172],"datasets":[173],"under":[174],"challenging":[177],"scenarios":[178],"demonstrate":[179],"WeSTAR":[181],"consistently":[182],"improves":[183],"achieves":[186],"state-of-the-art":[187],"across":[189],"wide":[191],"range":[192],"benchmarks.":[194]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}