{"id":"https://openalex.org/W4415708255","doi":"https://doi.org/10.1109/icme59968.2025.11209878","title":"Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models","display_name":"Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708255","doi":"https://doi.org/10.1109/icme59968.2025.11209878"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100362620","display_name":"Wenhao Li","orcid":"https://orcid.org/0000-0002-3642-2999"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wenhao Li","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011334334","display_name":"Xiu Su","orcid":"https://orcid.org/0000-0002-9863-5404"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Su","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462718","display_name":"Yu Han","orcid":"https://orcid.org/0000-0002-8976-1900"},"institutions":[{"id":"https://openalex.org/I167027274","display_name":"Nanjing Forestry University","ror":"https://ror.org/03m96p165","country_code":"CN","type":"education","lineage":["https://openalex.org/I167027274"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Han","raw_affiliation_strings":["Nanjing Forestry University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Forestry University","institution_ids":["https://openalex.org/I167027274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106825889","display_name":"Shan You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan You","raw_affiliation_strings":["Sensetime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sensetime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055915240","display_name":"Tao Huang","orcid":"https://orcid.org/0000-0002-9900-1112"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tao Huang","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001529504","display_name":"Chang Xu","orcid":"https://orcid.org/0000-0002-4756-0609"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chang Xu","raw_affiliation_strings":["University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34370498,"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":"6"},"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":0.7788000106811523,"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":0.7788000106811523,"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":0.03319999948143959,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.029500000178813934,"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/pruning","display_name":"Pruning","score":0.7376999855041504},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6912999749183655},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5940999984741211},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5730999708175659},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5321000218391418},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.48649999499320984},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4171000123023987}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7376999855041504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974999904632568},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6912999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258999705314636},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5940999984741211},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5730999708175659},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5321000218391418},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5084999799728394},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3873000144958496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36079999804496765},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3174000084400177},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3125},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.257099986076355},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2050654176","https://openalex.org/W2593414223","https://openalex.org/W2755577605","https://openalex.org/W2765811365","https://openalex.org/W2944465576","https://openalex.org/W3096831136","https://openalex.org/W3155072588","https://openalex.org/W4312933868","https://openalex.org/W4313142698","https://openalex.org/W4386066464","https://openalex.org/W4387806972","https://openalex.org/W4390873030"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"models":[1,19,77,132],"have":[2],"demonstrated":[3],"remarkable":[4],"efficacy":[5],"in":[6,32,154],"various":[7],"generative":[8],"tasks":[9],"with":[10],"the":[11,29,44,83,92,99,121,127,147],"predictive":[12],"prowess":[13],"of":[14,46,85,130,141,149,156,168],"denoising":[15,23,76,111,122],"model.":[16,112],"Currently,":[17],"diffusion":[18,47,86,131,142],"employ":[20],"a":[21,55,108,134],"uniform":[22],"model":[24,97],"across":[25],"all":[26],"timesteps.":[27],"However,":[28],"inherent":[30],"variations":[31],"data":[33],"distributions":[34],"at":[35],"different":[36],"timesteps":[37,66],"lead":[38],"to":[39,78,94,118,161],"conflicts":[40],"during":[41],"training,":[42],"constraining":[43],"potential":[45],"models.":[48,87,123,143],"To":[49],"address":[50],"this":[51],"challenge,":[52],"we":[53,114],"propose":[54],"novel":[56],"two-stage":[57,89],"divide-and-conquer":[58],"training":[59,90,101,107],"strategy":[60],"termed":[61],"TDC":[62,150],"Training.":[63],"It":[64],"groups":[65],"based":[67],"on":[68,158],"task":[69],"similarity":[70],"and":[71],"difficulty,":[72],"assigning":[73],"highly":[74],"customized":[75],"each":[79,96],"group,":[80],"thereby":[81],"enhancing":[82],"performance":[84],"While":[88],"avoids":[91],"need":[93],"train":[95],"separately,":[98],"total":[100],"cost":[102],"is":[103],"even":[104],"lower":[105],"than":[106],"single":[109],"unified":[110],"Additionally,":[113],"introduce":[115],"Proxy-based":[116],"Pruning":[117],"further":[119],"customize":[120],"This":[124],"method":[125],"transforms":[126],"pruning":[128,140],"problem":[129],"into":[133],"multi-round":[135],"decision-making":[136],"problem,":[137],"enabling":[138],"precise":[139],"Our":[144],"experiments":[145],"validate":[146],"effectiveness":[148],"Training,":[151],"demonstrating":[152],"improvements":[153],"FID":[155],"1.5":[157],"ImageNet64":[159],"compared":[160],"original":[162],"IDDPM,":[163],"while":[164],"saving":[165],"about":[166],"20%":[167],"computational":[169],"resources.":[170]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}