{"id":"https://openalex.org/W4417005428","doi":"https://doi.org/10.1109/wacv61042.2026.00090","title":"Boosting Medical Vision-Language Pretraining via Momentum Self-Distillation under Limited Computing Resources","display_name":"Boosting Medical Vision-Language Pretraining via Momentum Self-Distillation under Limited Computing Resources","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417005428","doi":"https://doi.org/10.1109/wacv61042.2026.00090"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00090","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/2512.02438","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011964600","display_name":"Phuc Huynh Pham","orcid":"https://orcid.org/0009-0005-6106-3421"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phuc Pham","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108786831","display_name":"Nh\u01b0 Hi\u1ec7p Ph\u1ea1m","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nhu Pham","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024762397","display_name":"Ngoc Quoc Ly","orcid":"https://orcid.org/0000-0003-4476-2456"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Ngoc Quoc Ly","raw_affiliation_strings":["University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I23582244"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03132221,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"860","last_page":"868"},"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":0.5092999935150146,"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":0.5092999935150146,"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":0.35429999232292175,"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":0.05009999871253967,"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/boosting","display_name":"Boosting (machine learning)","score":0.8514000177383423},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4959000051021576},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.40299999713897705},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.38109999895095825},{"id":"https://openalex.org/keywords/resource-efficiency","display_name":"Resource efficiency","score":0.35010001063346863},{"id":"https://openalex.org/keywords/momentum","display_name":"Momentum (technical analysis)","score":0.34279999136924744},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.3416000008583069}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8514000177383423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678999900817871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5758000016212463},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4959000051021576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4948999881744385},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C2777958785","wikidata":"https://www.wikidata.org/wiki/Q17120940","display_name":"Resource efficiency","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C60718061","wikidata":"https://www.wikidata.org/wiki/Q1414747","display_name":"Momentum (technical analysis)","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.3416000008583069},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C3019252630","wikidata":"https://www.wikidata.org/wiki/Q6549547","display_name":"Limited resources","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00090","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:2512.02438","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.02438","pdf_url":"https://arxiv.org/pdf/2512.02438","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.02438","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.02438","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.02438","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.02438","pdf_url":"https://arxiv.org/pdf/2512.02438","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":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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"medical":[1],"healthcare,":[2,66],"obtaining":[3],"detailed":[4],"annotations":[5],"is":[6,35,68,206],"challenging,":[7],"highlighting":[8],"the":[9,89,128,154],"need":[10],"for":[11,39,48],"robust":[12],"Vision-Language":[13],"Models":[14],"(VLMs).":[15],"Pretrained":[16],"VLMs":[17,41],"enable":[18],"fine-tuning":[19],"on":[20,87],"small":[21],"datasets":[22],"or":[23],"zero-shot":[24,146],"inference,":[25],"achieving":[26,157],"performance":[27,140,197],"comparable":[28],"to":[29,58,70,81,95,114,126,186],"task-specific":[30],"models.":[31],"Contrastive":[32],"learning":[33,190],"(CL)":[34],"a":[36,150,175],"key":[37],"paradigm":[38],"training":[40,80,172,181],"but":[42],"inherently":[43],"requires":[44],"large":[45],"batch":[46,130],"sizes":[47],"effective":[49,129],"learning,":[50,117],"making":[51],"it":[52,67],"computationally":[53],"demanding":[54],"and":[55,77,100,118,161],"often":[56],"limited":[57,63],"well-resourced":[59],"institutions.":[60],"Moreover,":[61],"with":[62,93,123,141,174],"data":[64,76],"in":[65,145,153],"important":[69],"prioritize":[71],"knowledge":[72,101],"extraction":[73],"from":[74],"both":[75],"models":[78],"during":[79],"improve":[82],"performance.":[83],"Therefore,":[84],"we":[85],"focus":[86],"leveraging":[88,111],"momentum":[90,112,121],"method":[91,137,169,205],"combined":[92],"distillation":[94],"simultaneously":[96],"address":[97],"computational":[98],"efficiency":[99,173],"exploitation.":[102],"Our":[103,136,183],"contributions":[104],"can":[105],"be":[106],"summarized":[107],"as":[108],"follows:":[109],"(1)":[110],"self-distillation":[113],"enhance":[115],"multimodal":[116,189],"(2)":[119],"integrating":[120],"mechanisms":[122],"gradient":[124],"accumulation":[125],"enlarge":[127],"size":[131],"without":[132],"increasing":[133],"resource":[134,193],"consumption.":[135],"attains":[138],"competitive":[139],"state-of-the-art":[142],"(SOTA)":[143],"approaches":[144],"classification,":[147],"while":[148,178,195],"providing":[149],"substantial":[151],"boost":[152],"few-shot":[155],"adaption,":[156],"over":[158,198],"90%":[159],"AUC-ROC":[160],"improving":[162,196],"retrieval":[163],"tasks":[164],"by":[165,191],"2\u20133%.":[166],"Importantly,":[167],"our":[168,204],"achieves":[170],"high":[171],"single":[176],"GPU":[177],"maintaining":[179],"reasonable":[180],"time.":[182],"approach":[184],"aims":[185],"advance":[187],"efficient":[188],"reducing":[192],"requirements":[194],"SOTA":[199],"methods.":[200],"The":[201],"implementation":[202],"of":[203],"available":[207],"at":[208],"https://github.com/phphuc612/MSD.":[209]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-12-04T00:00:00"}