{"id":"https://openalex.org/W4402716206","doi":"https://doi.org/10.1109/cvpr52733.2024.01339","title":"InstaGen: Enhancing Object Detection by Training on Synthetic Dataset","display_name":"InstaGen: Enhancing Object Detection by Training on Synthetic Dataset","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402716206","doi":"https://doi.org/10.1109/cvpr52733.2024.01339"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5101303327","display_name":"Chengjian Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chengjian Feng","raw_affiliation_strings":["Meituan Inc"],"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114911198","display_name":"Yujie Zhong","orcid":"https://orcid.org/0009-0007-9127-3387"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujie Zhong","raw_affiliation_strings":["Meituan Inc"],"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075329194","display_name":"Zequn Jie","orcid":"https://orcid.org/0000-0002-3038-5891"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zequn Jie","raw_affiliation_strings":["Meituan Inc"],"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053549250","display_name":"Weidi Xie","orcid":"https://orcid.org/0009-0002-8609-6826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidi Xie","raw_affiliation_strings":["CMIC, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"CMIC, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017116858","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan Inc"],"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101303327"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6743,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.95951205,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"14121","last_page":"14130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9991000294685364,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9962000250816345,"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/training","display_name":"Training (meteorology)","score":0.7305535078048706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6839913725852966},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5664279460906982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5416364073753357},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4725708067417145},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43913328647613525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38564035296440125},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3827507197856903},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07627815008163452}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7305535078048706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6839913725852966},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5664279460906982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5416364073753357},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4725708067417145},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43913328647613525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38564035296440125},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3827507197856903},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07627815008163452},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.01339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":44,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1959608418","https://openalex.org/W2194775991","https://openalex.org/W2423557781","https://openalex.org/W2948672349","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2983943451","https://openalex.org/W3092462694","https://openalex.org/W3096831136","https://openalex.org/W3138006590","https://openalex.org/W3166396011","https://openalex.org/W3173859428","https://openalex.org/W3203170887","https://openalex.org/W3204392079","https://openalex.org/W3206072662","https://openalex.org/W4214507171","https://openalex.org/W4221146106","https://openalex.org/W4224035735","https://openalex.org/W4226013992","https://openalex.org/W4226125322","https://openalex.org/W4281485151","https://openalex.org/W4300980715","https://openalex.org/W4310418579","https://openalex.org/W4312424618","https://openalex.org/W4312559104","https://openalex.org/W4312747482","https://openalex.org/W4312773012","https://openalex.org/W4312890493","https://openalex.org/W4312933868","https://openalex.org/W4324128075","https://openalex.org/W4386065751","https://openalex.org/W4386066010","https://openalex.org/W4386071614","https://openalex.org/W4386076029","https://openalex.org/W4386076396","https://openalex.org/W4390871935","https://openalex.org/W4390872357","https://openalex.org/W4390872587","https://openalex.org/W6620707391","https://openalex.org/W6809630927","https://openalex.org/W6838639034","https://openalex.org/W6856743786"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W4394050964","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W2551249631"],"abstract_inverted_index":{"In":[0],"this":[1,106],"paper,":[2],"we":[3,32],"present":[4],"a":[5,39,87,118],"novel":[6,88],"paradigm":[7],"to":[8,44,62,103,121],"enhance":[9,122],"the":[10,48,54,64,71,76,97],"ability":[11,49],"of":[12,50,67,75,109],"object":[13,84,123],"detector,":[14,85],"e.g.,":[15],"expanding":[16],"categories":[17,93],"or":[18],"improving":[19],"detection":[20],"performance,":[21],"by":[22,96,125],"training":[23,126],"on":[24,91,127],"syn-thetic":[25],"dataset":[26],"generated":[27,55,129],"from":[28,81],"diffusion":[29,42,77,110],"models.":[30],"Specifically,":[31],"integrate":[33],"an":[34,82],"instance-level":[35],"grounding":[36,58],"head":[37,59],"into":[38],"pre-trained,":[40],"generative":[41],"model,":[43,78,111],"augment":[45],"it":[46],"with":[47,70],"localising":[51],"instances":[52],"in":[53,138],"images.":[56],"The":[57],"is":[60],"trained":[61],"align":[63],"text":[65],"embedding":[66],"category":[68],"names":[69],"regional":[72],"visual":[73],"feature":[74],"using":[79],"supervision":[80],"off-the-shelf":[83],"and":[86,142],"self-training":[89],"scheme":[90],"(novel)":[92],"not":[94],"covered":[95],"detector.":[98],"We":[99],"conduct":[100],"thorough":[101],"experiments":[102],"show":[104],"that,":[105],"enhanced":[107],"version":[108],"termed":[112],"as":[113,117],"InstaGen,":[114],"can":[115],"serve":[116],"data":[119],"synthe-sizer,":[120],"detectors":[124],"its":[128],"samples,":[130],"demonstrating":[131],"superior":[132],"performance":[133],"over":[134],"existing":[135],"state-of-the-art":[136],"methods":[137],"open-vocabulary":[139],"(+4.5":[140],"AP)":[141,149],"data-sparse":[143],"(+":[144],"1.":[145],"2":[146],"~":[147],"5.2":[148],"scenarios.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}