{"id":"https://openalex.org/W7133190837","doi":"https://doi.org/10.52202/075280-3049","title":"DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets","display_name":"DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W7133190837","doi":"https://doi.org/10.52202/075280-3049"},"language":"en","primary_location":{"id":"doi:10.52202/075280-3049","doi":"https://doi.org/10.52202/075280-3049","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-3049","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.04894","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126634875","display_name":"Yash Jain","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yash Jain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081255348","display_name":"Harkirat Singh Behl","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harkirat Behl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099124138","display_name":"Zsolt Kira","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zsolt Kira","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045147286","display_name":"Vibhav Vineet","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vibhav Vineet","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":1.53,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90117702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"69625","last_page":"69637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5083000063896179,"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":0.5083000063896179,"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":0.23340000212192535,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2273000031709671,"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/mixture-of-experts","display_name":"mixture of experts","score":0.8790000081062317},{"id":"https://openalex.org/keywords/visual-understanding","display_name":"visual understanding","score":0.875},{"id":"https://openalex.org/keywords/multi-dataset-learning","display_name":"multi-dataset learning","score":0.5849999785423279},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.3880000114440918},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45329999923706055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.24860000610351562},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2433999925851822}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/075280-3049","doi":"https://doi.org/10.52202/075280-3049","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-3049","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2311.04894","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.04894","pdf_url":"https://arxiv.org/pdf/2311.04894","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,"listed_in":[],"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.2311.04894","doi":"https://doi.org/10.48550/arxiv.2311.04894","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.04894","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.04894","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.04894","pdf_url":"https://arxiv.org/pdf/2311.04894","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133190837.pdf","grobid_xml":"https://content.openalex.org/works/W7133190837.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2581624817","https://openalex.org/W2807007689","https://openalex.org/W2885106262","https://openalex.org/W2955639361","https://openalex.org/W3040573126","https://openalex.org/W3184439416","https://openalex.org/W3206606249","https://openalex.org/W3215626407","https://openalex.org/W4221146106","https://openalex.org/W4283208789","https://openalex.org/W4390874575"],"related_works":["https://openalex.org/W7155091969","https://openalex.org/W4387156594","https://openalex.org/W7151265459","https://openalex.org/W7162511196","https://openalex.org/W4312456860","https://openalex.org/W6997122939","https://openalex.org/W2784138599","https://openalex.org/W6947803890","https://openalex.org/W4391353242","https://openalex.org/W7160227185"],"abstract_inverted_index":{"Construction":[0],"of":[1,21,97],"a":[2,6,15,18,39,52,59,71,80,98],"universal":[3],"detector":[4],"poses":[5],"crucial":[7],"question:":[8],"How":[9],"can":[10],"we":[11,67,89,118,160],"most":[12],"effectively":[13],"train":[14,90],"model":[16],"on":[17,51,112],"large":[19],"mixture":[20],"datasets?":[22],"The":[23],"answer":[24],"lies":[25],"in":[26,38,58,62],"learning":[27,101],"dataset-specific":[28],"features":[29],"and":[30,128,154],"ensembling":[31],"their":[32],"knowledge":[33],"but":[34,55],"do":[35],"all":[36],"this":[37,45,65],"single":[40],"model.":[41],"Previous":[42],"methods":[43],"achieve":[44],"by":[46,100,123,134],"having":[47],"separate":[48],"detection":[49],"heads":[50],"common":[53],"backbone":[54],"that":[56,74,117,163],"results":[57],"significant":[60],"increase":[61],"parameters.":[63],"In":[64],"work,":[66],"present":[68],"Mixture-of-Experts":[69],"as":[70],"solution,":[72],"highlighting":[73],"MoEs":[75],"are":[76],"much":[77],"more":[78],"than":[79],"scalability":[81],"tool.":[82],"We":[83,139],"propose":[84],"Dataset-Aware":[85],"Mixture-of-Experts,":[86],"DAMEX":[87,164],"where":[88],"the":[91,120],"experts":[92],"to":[93,102,107],"become":[94],"an":[95],"`expert'":[96],"dataset":[99,105],"route":[103],"each":[104],"tokens":[106],"its":[108],"mapped":[109],"expert.":[110],"Experiments":[111],"Universal":[113],"Object-Detection":[114],"Benchmark":[115],"show":[116,162],"outperform":[119],"existing":[121],"state-of-the-art":[122],"average":[124,135],"+10.2":[125],"AP":[126,137],"score":[127],"improve":[129],"over":[130],"our":[131],"non-MoE":[132],"baseline":[133],"+2.0":[136],"score.":[138],"also":[140],"observe":[141],"consistent":[142],"gains":[143],"while":[144],"mixing":[145],"datasets":[146],"with":[147],"(1)":[148],"limited":[149],"availability,":[150],"(2)":[151],"disparate":[152],"domains":[153],"(3)":[155],"divergent":[156],"label":[157],"sets.":[158],"Further,":[159],"qualitatively":[161],"is":[165],"robust":[166],"against":[167],"expert":[168],"representation":[169],"collapse.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-03-03T00:00:00"}