{"id":"https://openalex.org/W4415538137","doi":"https://doi.org/10.1145/3746027.3754902","title":"DRMix: Decomposition-Recomposition Data Augmentation with Diffusion Model","display_name":"DRMix: Decomposition-Recomposition Data Augmentation with Diffusion Model","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538137","doi":"https://doi.org/10.1145/3746027.3754902"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5029500387","display_name":"S. T. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0005-9410-4058","affiliations":[{"raw_affiliation_string":"College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000118907","display_name":"Zhichuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichuan Wang","raw_affiliation_strings":["College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0003-5886-1639","affiliations":[{"raw_affiliation_string":"College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanmin Chen","orcid":"https://orcid.org/0009-0000-2564-2753"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Chen","raw_affiliation_strings":["College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0000-2564-2753","affiliations":[{"raw_affiliation_string":"College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111020085","display_name":"Mengyao Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyao Zhou","raw_affiliation_strings":["College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0009-4546-7804","affiliations":[{"raw_affiliation_string":"College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I204823248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100519540","display_name":"Jun Luo","orcid":"https://orcid.org/0000-0002-2663-0479"},"institutions":[{"id":"https://openalex.org/I204823248","display_name":"Huazhong Agricultural University","ror":"https://ror.org/023b72294","country_code":"CN","type":"education","lineage":["https://openalex.org/I204823248"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Luo","raw_affiliation_strings":["College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0002-2663-0479","affiliations":[{"raw_affiliation_string":"College of Informatics, Huazhong Agricultural University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I204823248"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204823248"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32690431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7481","last_page":"7489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9929999709129333,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9929999709129333,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6470000147819519},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6248000264167786},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6133000254631042},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5866000056266785},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.48739999532699585},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4706999957561493},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44040000438690186},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4343999922275543},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.429500013589859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.671500027179718},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6470000147819519},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6248000264167786},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6133000254631042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086000204086304},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4927000105381012},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.48739999532699585},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.42179998755455017},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.3612000048160553},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2897999882698059},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.2648000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2623000144958496},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G315266592","display_name":null,"funder_award_id":"2662025PY019","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2138011018","https://openalex.org/W3175248300","https://openalex.org/W4320002812","https://openalex.org/W4382240652"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"models":[1,25],"have":[2,50],"emerged":[3],"as":[4,43,45],"powerful":[5],"tools":[6],"capable":[7],"of":[8,16],"generating":[9],"photorealistic":[10],"images,":[11],"spawning":[12],"a":[13,110],"wide":[14],"range":[15],"applications":[17],"across":[18,125],"various":[19],"domains.":[20],"However,":[21],"effectively":[22],"integrating":[23],"generative":[24,39],"into":[26,83],"image":[27,104,129],"classification":[28],"tasks":[29],"remains":[30],"an":[31,74],"open":[32],"problem.":[33],"Our":[34],"analysis":[35],"reveals":[36],"that":[37,120],"current":[38],"data":[40,47,77],"augmentation":[41,48,78],"methods,":[42],"well":[44],"traditional":[46],"techniques,":[49],"limitations":[51],"in":[52],"simultaneously":[53],"ensuring":[54],"both":[55,102],"fidelity":[56,114],"(faithful":[57],"foreground)":[58],"and":[59,85,93,105,108,115,133],"diversity":[60,99],"(rich":[61],"background":[62,91],"contexts).":[63],"To":[64],"address":[65],"this":[66],"challenge,":[67],"we":[68],"propose":[69],"Decomposition-Recomposition":[70],"Data":[71],"Augmentation":[72],"(DRMix),":[73],"innovative":[75],"intra-class":[76,94],"method.":[79],"DRMix":[80,121],"decomposes":[81],"images":[82],"foreground-background":[84],"foreground":[86,95],"parts,":[87],"then":[88],"performs":[89],"diversified":[90],"recomposition":[92],"recomposition,":[96],"achieving":[97],"dual":[98],"enhancement":[100],"at":[101],"the":[103],"part":[106],"levels,":[107],"strikes":[109],"better":[111],"trade-off":[112],"between":[113],"diversity.":[116],"Experimental":[117],"results":[118],"demonstrate":[119],"significantly":[122],"improves":[123],"performance":[124],"multiple":[126],"tasks,":[127],"including":[128],"classification,":[130],"few-shot":[131],"learning,":[132],"weakly-supervised":[134],"object":[135],"localization":[136],"(WSOL).":[137]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}