{"id":"https://openalex.org/W7160359660","doi":"https://doi.org/10.1109/wacv61042.2026.00188","title":"Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models","display_name":"Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160359660","doi":"https://doi.org/10.1109/wacv61042.2026.00188"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5099083063","display_name":"Oz Zafar","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Oz Zafar","raw_affiliation_strings":["Tel-Aviv University,Tel Aviv,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel-Aviv University,Tel Aviv,Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000885878","display_name":"Y. Cohen","orcid":"https://orcid.org/0000-0002-7949-0721"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yuval Cohen","raw_affiliation_strings":["Tel-Aviv University,Tel Aviv,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel-Aviv University,Tel Aviv,Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135394413","display_name":"Lior Wolf","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lior Wolf","raw_affiliation_strings":["Tel-Aviv University,Tel Aviv,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel-Aviv University,Tel Aviv,Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082617813","display_name":"Idan Schwartz","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Idan Schwartz","raw_affiliation_strings":["Tel-Aviv University,Tel Aviv,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel-Aviv University,Tel Aviv,Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":21.6816,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9902088,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1885","last_page":"1894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.17170000076293945,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.17170000076293945,"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":0.05640000104904175,"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":0.05400000140070915,"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/object","display_name":"Object (grammar)","score":0.5235999822616577},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.3993000090122223},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.2809000015258789},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.26019999384880066}],"concepts":[{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4781000018119812},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40400001406669617},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37059998512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3328999876976013},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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":23,"referenced_works":["https://openalex.org/W2008590470","https://openalex.org/W3153469116","https://openalex.org/W3170764266","https://openalex.org/W4312282373","https://openalex.org/W4312933868","https://openalex.org/W4382059335","https://openalex.org/W4385270985","https://openalex.org/W4385775296","https://openalex.org/W4386072096","https://openalex.org/W4386076027","https://openalex.org/W4386076532","https://openalex.org/W4390871835","https://openalex.org/W4390873054","https://openalex.org/W4390873321","https://openalex.org/W4390873331","https://openalex.org/W4402716119","https://openalex.org/W4402951630","https://openalex.org/W4403757510","https://openalex.org/W4409264082","https://openalex.org/W4413147601","https://openalex.org/W7133185348","https://openalex.org/W7133196220","https://openalex.org/W7133221421"],"related_works":[],"abstract_inverted_index":{"Accurately":[0],"controlling":[1],"object":[2,61,122,126,209],"count":[3,21],"in":[4],"text-to-image":[5],"generation":[6],"remains":[7],"a":[8,50,116,134,149],"key":[9],"challenge.":[10],"Supervised":[11],"methods":[12],"often":[13],"fail,":[14],"as":[15],"training":[16],"data":[17],"rarely":[18],"covers":[19],"all":[20],"variations.":[22],"Methods":[23],"that":[24,57,90,119,153,173],"manipulate":[25],"the":[26,167,174,184],"denoising":[27,88],"process":[28],"to":[29,100,128],"add":[30],"or":[31],"remove":[32],"objects":[33],"can":[34,177],"help;":[35],"however,":[36],"they":[37,77,96],"still":[38],"require":[39],"labeled":[40],"data,":[41],"limit":[42],"robustness":[43],"and":[44,47,65,103,125,159,202],"image":[45],"quality,":[46],"rely":[48,58],"on":[49,59,80,92,142],"slow,":[51],"iterative":[52],"process.Pre-trained":[53],"differentiable":[54],"counting":[55,123,135,206],"models":[56],"soft":[60],"density":[62],"summation":[63],"exist":[64],"could":[66],"steer":[67],"generation,":[68],"but":[69],"employing":[70],"them":[71,84],"presents":[72],"three":[73],"main":[74],"challenges:":[75],"(i)":[76],"are":[78,97],"pre-trained":[79,121],"clean":[81],"images,":[82],"making":[83],"less":[85],"effective":[86],"during":[87],"steps":[89],"operate":[91],"noisy":[93],"inputs;":[94],"(ii)":[95],"not":[98],"robust":[99],"viewpoint":[101,158],"changes;":[102],"(iii)":[104],"optimization":[105],"is":[106],"computationally":[107],"expensive,":[108],"requiring":[109,164],"repeated":[110,187],"model":[111],"evaluations":[112],"per":[113],"image.We":[114],"propose":[115],"new":[117,181],"framework":[118],"uses":[120],"techniques":[124],"detectors":[127],"guide":[129],"generation.":[130],"First,":[131],"we":[132,147,171],"optimize":[133],"token":[136,194],"using":[137],"an":[138],"outer-loop":[139],"loss":[140],"computed":[141],"fully":[143],"generated":[144],"images.":[145],"Second,":[146],"introduce":[148],"detection-driven":[150],"scaling":[151],"term":[152],"corrects":[154],"errors":[155],"caused":[156],"by":[157],"proportion":[160],"shifts,":[161],"etc.,":[162],"without":[163],"backpropagation":[165],"through":[166,193],"detection":[168],"model.":[169],"Third,":[170],"show":[172],"optimized":[175],"parameters":[176],"be":[178],"reused":[179],"for":[180,186],"prompts,":[182],"removing":[183],"need":[185],"optimization.":[188],"Our":[189],"method":[190],"provides":[191],"efficiency":[192],"reuse,":[195],"flexibility":[196],"via":[197],"compatibility":[198],"with":[199,204],"various":[200],"detectors,":[201],"accuracy":[203],"improved":[205],"across":[207],"diverse":[208],"categories.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}