{"id":"https://openalex.org/W4414739275","doi":"https://doi.org/10.1109/iccv51701.2025.02124","title":"Boosting Multimodal Learning via Disentangled Gradient Learning","display_name":"Boosting Multimodal Learning via Disentangled Gradient Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414739275","doi":"https://doi.org/10.1109/iccv51701.2025.02124"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.10213","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025767081","display_name":"Shicai Wei","orcid":"https://orcid.org/0000-0001-5744-2035"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shicai Wei","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038985671","display_name":"Chunbo Luo","orcid":"https://orcid.org/0000-0002-9860-2901"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunbo Luo","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115594805","display_name":"Yang Luo","orcid":"https://orcid.org/0000-0003-4536-3457"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Luo","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025767081"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13331208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8299999833106995,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.8299999833106995,"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/T10057","display_name":"Face and Expression Recognition","score":0.7131999731063843,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.704800009727478,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7932000160217285},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7437000274658203},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6212000250816345},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4207000136375427},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.41269999742507935},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.3815999925136566},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.3716000020503998},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3707999885082245}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7932000160217285},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7437000274658203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6766999959945679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6310999989509583},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6212000250816345},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.3815999925136566},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30230000615119934},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C10494615","wikidata":"https://www.wikidata.org/wiki/Q17086765","display_name":"Proximal Gradient Methods","level":4,"score":0.26460000872612},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25279998779296875},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.10213","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10213","pdf_url":"https://arxiv.org/pdf/2507.10213","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2507.10213","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.10213","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.10213","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10213","pdf_url":"https://arxiv.org/pdf/2507.10213","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"learning":[1,23,118],"often":[2],"encounters":[3],"the":[4,21,38,55,59,73,80,93,99,107,123,126,134,139,143,147,154,162,166,170,177,181,210,215],"under-optimized":[5],"problem":[6,19],"and":[7,26,62,129,150,184,203,212],"may":[8],"have":[9],"worse":[10],"performance":[11,94],"than":[12],"unimodal":[13,48,90,108,157,167],"learning.":[14,49],"Existing":[15],"methods":[16],"attribute":[17],"this":[18,51,111],"to":[20,35,84,104,121,146,169],"imbalanced":[22],"between":[24,58,180],"modalities":[25],"rebalance":[27],"them":[28],"through":[29],"gradient":[30,81,117,140,155,163,178],"modulation.":[31],"However,":[32],"they":[33],"fail":[34],"explain":[36],"why":[37],"dominant":[39],"modality":[40,60,63,86,97,127,130,148,171,182,185],"in":[41,47,66,76,98,106,133],"multimodal":[42,67,77,100,135,144],"models":[43,78],"also":[44],"underperforms":[45],"that":[46,72,105],"In":[50],"work,":[52],"we":[53,70,113],"reveal":[54],"optimization":[56,124,192],"conflict":[57],"encoder":[61,87,128,149,183],"fusion":[64,75,131,172,186],"module":[65,132,187],"models.":[68,91],"Specifically,":[69],"prove":[71],"cross-modal":[74,207],"decreases":[79],"passed":[82],"back":[83],"each":[85,96],"compared":[88],"with":[89,153,205],"Consequently,":[92],"of":[95,125,200,214],"model":[101],"is":[102,219],"inferior":[103],"model.":[109,136],"To":[110],"end,":[112],"propose":[114],"a":[115],"disentangled":[116],"(DGL)":[119],"framework":[120],"decouple":[122],"DGL":[137,160],"truncates":[138],"back-propagated":[141,164],"from":[142,156,165],"loss":[145,168],"replaces":[151],"it":[152],"loss.":[158],"Besides,":[159],"removes":[161],"module.":[173],"This":[174],"helps":[175],"eliminate":[176],"interference":[179],"while":[188],"ensuring":[189],"their":[190],"respective":[191],"processes.":[193],"Finally,":[194],"extensive":[195],"experiments":[196],"on":[197],"multiple":[198],"types":[199],"modalities,":[201],"tasks,":[202],"frameworks":[204],"dense":[206],"interaction":[208],"demonstrate":[209],"effectiveness":[211],"versatility":[213],"proposed":[216],"DGL.":[217],"Code":[218],"available":[220],"at":[221],"\\href{https://github.com/shicaiwei123/ICCV2025-GDL}{https://github.com/shicaiwei123/ICCV2025-GDL}":[222]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}