{"id":"https://openalex.org/W4415708099","doi":"https://doi.org/10.1109/icme59968.2025.11209208","title":"SparseDM: Toward Sparse Efficient Diffusion Models","display_name":"SparseDM: Toward Sparse Efficient Diffusion Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708099","doi":"https://doi.org/10.1109/icme59968.2025.11209208"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209208","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":"article","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/A5104282905","display_name":"Kafeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kafeng Wang","raw_affiliation_strings":["Tsinghua University,Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab,Dept. of Comp. Sci. & Tech.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab,Dept. of Comp. Sci. & Tech.,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianfei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfei Chen","raw_affiliation_strings":["Tsinghua University,Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab,Dept. of Comp. Sci. & Tech.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab,Dept. of Comp. Sci. & Tech.,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317874","display_name":"He Li","orcid":"https://orcid.org/0000-0002-6219-9911"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Li","raw_affiliation_strings":["Tsinghua University,Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab,Dept. of Comp. Sci. & Tech.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab,Dept. of Comp. Sci. & Tech.,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104282906","display_name":"Zhenpeng Mi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenpeng Mi","raw_affiliation_strings":["Honor Device Co., Ltd.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Honor Device Co., Ltd.,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103865065","display_name":"Jun Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhu","raw_affiliation_strings":["Tsinghua University,Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab,Dept. of Comp. Sci. & Tech.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute for AI, BNRist Center, Tsinghua-Bosch Joint ML Center, THBI Lab,Dept. of Comp. Sci. & Tech.,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104282905"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.1828,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84252008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.8709999918937683,"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":0.8709999918937683,"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":0.010599999688565731,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.009200000204145908,"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/inference","display_name":"Inference","score":0.5814999938011169},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5562000274658203},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4702000021934509},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4530999958515167},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.40869998931884766},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3366999924182892},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.335999995470047},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.31859999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557000279426575},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5080000162124634},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4530999958515167},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.40869998931884766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25519999861717224},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209208","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W4312933868","https://openalex.org/W4386047807","https://openalex.org/W4390872297","https://openalex.org/W4402917085"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"models":[1,8,98,111],"represent":[2],"a":[3,40,68,93],"powerful":[4],"family":[5],"of":[6,53],"generative":[7],"widely":[9],"used":[10],"for":[11],"image":[12],"and":[13,23,64,82,95],"video":[14],"generation.":[15],"However,":[16],"the":[17,44,50,62,75,79,85,118,124],"time-consuming":[18],"deployment,":[19],"long":[20],"inference":[21],"time,":[22],"requirements":[24],"on":[25,31,43,84,92,117],"large":[26],"memory":[27],"hinder":[28],"their":[29],"applications":[30],"resource":[32],"constrained":[33],"devices.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,57],"propose":[39],"method":[41,102],"based":[42],"improved":[45],"Straight-Through":[46],"Estimator":[47],"to":[48,61,132],"improve":[49],"deployment":[51],"efficiency":[52],"diffusion":[54,70,97],"models.":[55],"Specifically,":[56],"add":[58],"sparse":[59,76,86],"masks":[60,87],"Convolution":[63],"Linear":[65],"layers":[66],"in":[67],"pre-trained":[69],"model,":[71],"then":[72],"transfer":[73],"learn":[74],"model":[77],"during":[78,88],"fine-tuning":[80],"stage":[81],"turn":[83],"inference.":[89],"Experimental":[90],"results":[91],"Transformer":[94],"UNet-based":[96],"demonstrate":[99],"that":[100],"our":[101],"reduces":[103],"MACs":[104,122],"by":[105,114],"50%":[106],"while":[107],"maintaining":[108],"FID.":[109],"Sparse":[110],"are":[112],"accelerated":[113],"approximately":[115],"1.2x":[116],"GPU.":[119],"Under":[120],"other":[121,133],"conditions,":[123],"FID":[125],"is":[126],"also":[127],"lower":[128],"than":[129],"1":[130],"compared":[131],"methods.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-30T00:00:00"}