{"id":"https://openalex.org/W4406325054","doi":"https://doi.org/10.1145/3712064","title":"DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous Driving Data Generation","display_name":"DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous Driving Data Generation","publication_year":2025,"publication_date":"2025-01-13","ids":{"openalex":"https://openalex.org/W4406325054","doi":"https://doi.org/10.1145/3712064"},"language":"en","primary_location":{"id":"doi:10.1145/3712064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712064","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/A5108332199","display_name":"Jiahang Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahang Tu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0009-0000-2763-6840","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101397422","display_name":"Wei Ji","orcid":"https://orcid.org/0000-0002-8106-9768"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Ji","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore","National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-8106-9768","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007599551","display_name":"Hanbin Zhao","orcid":"https://orcid.org/0000-0001-8906-4534"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanbin Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0001-8906-4534","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103386985","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0001-7174-8663"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0001-7174-8663","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058575315","display_name":"Roger Zimmermann","orcid":"https://orcid.org/0000-0002-7410-2590"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Roger Zimmermann","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore","National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7410-2590","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101960126","display_name":"Hui Qian","orcid":"https://orcid.org/0000-0003-0293-2656"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Qian","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0003-0293-2656","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2966,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8661497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"21","issue":"3","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983999729156494,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.903998613357544},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5297765731811523},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4887787997722626},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4303451180458069},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4148067235946655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40506279468536377},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3325577974319458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.903998613357544},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5297765731811523},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4887787997722626},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4303451180458069},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4148067235946655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40506279468536377},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3325577974319458},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712064","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712064","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2150066425","https://openalex.org/W2533598788","https://openalex.org/W2603777577","https://openalex.org/W2914911817","https://openalex.org/W2937274663","https://openalex.org/W2963037989","https://openalex.org/W2963981733","https://openalex.org/W3035172746","https://openalex.org/W3035564946","https://openalex.org/W3035574168","https://openalex.org/W3096831136","https://openalex.org/W3176828726","https://openalex.org/W4298054444","https://openalex.org/W4312543476","https://openalex.org/W4312651322","https://openalex.org/W4312933868","https://openalex.org/W4386047807","https://openalex.org/W4386071957","https://openalex.org/W4386072096","https://openalex.org/W4388979610","https://openalex.org/W4390872297","https://openalex.org/W4393147567","https://openalex.org/W4398756379","https://openalex.org/W6739901393","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W2355833770","https://openalex.org/W1985458517","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2050451745","https://openalex.org/W2378903222"],"abstract_inverted_index":{"In":[0],"autonomous":[1,69],"driving,":[2],"deep":[3],"models":[4],"have":[5],"shown":[6],"remarkable":[7],"performance":[8],"across":[9],"various":[10,29],"visual":[11],"perception":[12],"tasks":[13],"with":[14,32],"the":[15,53,104,107,112,131,148,159,177],"demand":[16],"of":[17,56,150,172],"high-quality":[18,170],"and":[19,37,49,94,111,122,157],"huge-diversity":[20],"training":[21,166],"datasets.":[22],"Such":[23],"datasets":[24,185],"are":[25],"expected":[26],"to":[27,91,103,127,146,162],"cover":[28],"driving":[30,114,184,195],"scenarios":[31],"adverse":[33],"weather,":[34],"lighting":[35,123],"conditions,":[36],"diverse":[38,193],"moving":[39,174],"objects.":[40],"However,":[41],"manually":[42],"collecting":[43],"these":[44],"data":[45,72,110],"presents":[46],"huge":[47],"challenges":[48],"is":[50,135],"expensive.":[51],"With":[52],"rapid":[54],"development":[55],"large":[57],"generative":[58],"models,":[59],"we":[60],"propose":[61],"DriveDiTFit,":[62],"a":[63,87,97,138],"novel":[64],"method":[65,189],"for":[66],"efficiently":[67,95,191],"generating":[68],"Driv":[70],"ing":[71],"by":[73,137],"Fi":[74],"ne-":[75],"t":[76],"uning":[77],"pre-trained":[78,108],"Di":[79],"ffusion":[80],"T":[81],"ransformers":[82],"(DiTs).":[83],"Specifically,":[84],"DriveDiTFit":[85,117,168],"utilizes":[86],"gap-driven":[88],"modulation":[89],"technique":[90],"carefully":[92],"select":[93],"fine-tune":[96],"few":[98],"parameters":[99],"in":[100,130,153,165,176],"DiTs":[101],"according":[102],"discrepancy":[105],"between":[106],"source":[109],"target":[113],"data.":[115,179,196],"Additionally,":[116],"develops":[118],"an":[119],"effective":[120],"weather":[121],"condition":[124],"embedding":[125],"module":[126],"ensure":[128],"diversity":[129],"generated":[132,178],"data,":[133],"which":[134],"initialized":[136],"nearest-semantic-similarity":[139],"initialization":[140],"approach.":[141],"Through":[142],"progressive":[143],"tuning":[144],"scheme":[145],"refine":[147],"process":[149,156],"detail":[151],"generation":[152,171],"early":[154],"diffusion":[155],"enlarging":[158],"weights":[160],"corresponding":[161],"small":[163,173],"objects":[164,175],"loss,":[167],"ensures":[169],"Extensive":[180],"experiments":[181],"conducted":[182],"on":[183],"confirm":[186],"that":[187],"our":[188],"could":[190],"produce":[192],"real":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
