{"id":"https://openalex.org/W4407031113","doi":"https://doi.org/10.1145/3715915","title":"SOEDiff: Efficient Distillation for Small Object Editing","display_name":"SOEDiff: Efficient Distillation for Small Object Editing","publication_year":2025,"publication_date":"2025-01-31","ids":{"openalex":"https://openalex.org/W4407031113","doi":"https://doi.org/10.1145/3715915"},"language":"en","primary_location":{"id":"doi:10.1145/3715915","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3715915","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5101490743","display_name":"Yiming Wu","orcid":"https://orcid.org/0000-0002-9866-669X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yiming Wu","raw_affiliation_strings":["College of Computer Science, Zhejiang University of Technology, Hangzhou, China and The University of Hong Kong, Hong Kong, China","Zhejiang University of Technology, China and The University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-9866-669X","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University of Technology, Hangzhou, China and The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168879160","https://openalex.org/I55712492","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Zhejiang University of Technology, China and The University of Hong Kong, China","institution_ids":["https://openalex.org/I55712492","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101355242","display_name":"Qihe Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihe Pan","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China","Zhejiang University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0007-4660-5549","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"Zhejiang University of Technology, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072694516","display_name":"Zhen Zhao","orcid":"https://orcid.org/0000-0002-0796-4078"},"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":"Zhen Zhao","raw_affiliation_strings":["The University of Sydney, Sydney, Australia","The University of Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0796-4078","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"The University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347959","display_name":"Zicheng Wang","orcid":"https://orcid.org/0000-0001-8351-0329"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zicheng Wang","raw_affiliation_strings":["College of Computer Science, The University of Hong Kong, Hong Kong, China","The University of Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-8351-0329","affiliations":[{"raw_affiliation_string":"College of Computer Science, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"The University of Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102874282","display_name":"Sifan Long","orcid":"https://orcid.org/0000-0001-7060-1133"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210136497","display_name":"Jilin Medical University","ror":"https://ror.org/03mzw7781","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136497"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sifan Long","raw_affiliation_strings":["Jilin University, Changchun, China","Jilin University, China"],"raw_orcid":"https://orcid.org/0000-0001-7060-1133","affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]},{"raw_affiliation_string":"Jilin University, China","institution_ids":["https://openalex.org/I4210136497","https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001531117","display_name":"Ronghua Liang","orcid":"https://orcid.org/0000-0003-2077-9608"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghua Liang","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China","Zhejiang University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-2077-9608","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]},{"raw_affiliation_string":"Zhejiang University of Technology, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8412,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83338103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"21","issue":"11","first_page":"1","last_page":"19"},"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":0.9988999962806702,"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":0.9988999962806702,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.987500011920929,"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":0.9811000227928162,"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/computer-science","display_name":"Computer science","score":0.8911635875701904},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.7652490139007568},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.7028888463973999},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.698905348777771},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6304309964179993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6007658243179321},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5951741337776184},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.540022611618042},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5111783146858215},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49903011322021484},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4513881504535675},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.43749138712882996},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39687028527259827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8911635875701904},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.7652490139007568},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7028888463973999},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.698905348777771},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6304309964179993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6007658243179321},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5951741337776184},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.540022611618042},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5111783146858215},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49903011322021484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4513881504535675},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.43749138712882996},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39687028527259827},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3715915","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3715915","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G65978832","display_name":null,"funder_award_id":"62202431, 62036009, and 2020YFB1707700","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2981852735","https://openalex.org/W3036167779","https://openalex.org/W4281485151","https://openalex.org/W4288089799","https://openalex.org/W4321277285","https://openalex.org/W4385271281","https://openalex.org/W4386076027","https://openalex.org/W4393148714","https://openalex.org/W4403791183","https://openalex.org/W4403792529","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W2244018504","https://openalex.org/W4242046654","https://openalex.org/W3174923100","https://openalex.org/W3134074939","https://openalex.org/W2117562399","https://openalex.org/W3027110395","https://openalex.org/W3109174731","https://openalex.org/W4285125754"],"abstract_inverted_index":{"In":[0,164],"this":[1],"article,":[2],"we":[3,87,176],"delve":[4],"into":[5],"a":[6,22,89,178,184],"new":[7],"task":[8,43],"known":[9],"as":[10,50],"Small":[11],"Object":[12,51],"Editing":[13],"(SOE),":[14],"which":[15,79,121,131],"focuses":[16],"on":[17,146,172],"text-based":[18],"image":[19,35],"inpainting":[20,36],"within":[21],"constrained,":[23],"small-sized":[24,66,106],"area.":[25],"Despite":[26],"the":[27,41,62,72,97,136,147,156,173],"remarkable":[28],"success":[29],"have":[30],"been":[31],"achieved":[32],"by":[33,76],"current":[34],"approaches,":[37],"their":[38],"application":[39],"to":[40],"SOE":[42],"generally":[44],"results":[45],"in":[46,68,104,162,181,188],"failure":[47],"cases":[48],"such":[49],"Missing,":[52],"Text-Image":[53],"Mismatch,":[54],"and":[55,71,126,153,183],"Distortion":[56],".":[57],"These":[58],"failures":[59],"stem":[60],"from":[61,135,151],"limited":[63],"use":[64],"of":[65,99,158,186],"objects":[67,107],"training":[69,110],"datasets":[70],"down-sampling":[73],"operations":[74],"employed":[75],"U-Net":[77],"models,":[78],"hinders":[80],"accurate":[81],"generation.":[82],"To":[83],"overcome":[84],"these":[85],"challenges,":[86],"introduce":[88],"novel":[90],"training-based":[91],"approach,":[92],"SOEDiff,":[93],"aimed":[94],"at":[95],"enhancing":[96],"capability":[98],"baseline":[100],"models":[101],"like":[102],"StableDiffusion":[103],"editing":[105],"while":[108],"minimizing":[109],"costs.":[111],"Specifically,":[112],"our":[113,159],"method":[114,142,161],"involves":[115],"two":[116],"key":[117],"components:":[118],"SO-LoRA":[119],",":[120,130],"efficiently":[122],"fine-tunes":[123],"low-rank":[124],"matrices,":[125],"Cross-scale":[127],"score":[128],"distillation":[129],"leverages":[132],"high-resolution":[133],"predictions":[134],"pre-trained":[137],"teacher":[138],"diffusion":[139],"model.":[140],"Our":[141],"presents":[143],"significant":[144],"improvements":[145],"test":[148],"dataset":[149],"collected":[150],"MSCOCO":[152],"OpenImage,":[154],"validating":[155],"effectiveness":[157],"proposed":[160],"SOE.":[163],"particular,":[165],"when":[166],"comparing":[167],"SOEDiff":[168],"with":[169],"SD-I":[170],"model":[171],"OpenImage-small-val":[174],"dataset,":[175],"observe":[177],"0.99":[179],"improvement":[180],"CLIP-Score":[182],"reduction":[185],"2.87":[187],"FID.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2025-10-10T00:00:00"}