{"id":"https://openalex.org/W4415536897","doi":"https://doi.org/10.1145/3746027.3754959","title":"Object-Preserving Counterfactual Diffusion Augmentation for Single-Domain Generalized Object Detection","display_name":"Object-Preserving Counterfactual Diffusion Augmentation for Single-Domain Generalized Object Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536897","doi":"https://doi.org/10.1145/3746027.3754959"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754959","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5021345611","display_name":"Hongda Qin","orcid":"https://orcid.org/0000-0003-2687-6505"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongda Qin","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, Guangxi, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, Guangxi, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002166815","display_name":"Xiao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Lu","raw_affiliation_strings":["College of Engineering and Design, Hunan Normal University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Engineering and Design, Hunan Normal University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101234368","display_name":"Zhiyong Wei","orcid":"https://orcid.org/0009-0003-5422-1116"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wei","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning, Guangxi, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning, Guangxi, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034212921","display_name":"Ningjiang Chen","orcid":"https://orcid.org/0000-0003-0187-6760"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningjiang Chen","raw_affiliation_strings":["Graduate School, Guangxi University, Nanning, Guangxi, China"],"affiliations":[{"raw_affiliation_string":"Graduate School, Guangxi University, Nanning, Guangxi, China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021345611"],"corresponding_institution_ids":["https://openalex.org/I150807315"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84493353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"189","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.996999979019165,"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":0.996399998664856,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.7476000189781189},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6176999807357788},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5974000096321106},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5480999946594238},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5404999852180481},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5278000235557556},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5065000057220459},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.498199999332428}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.7476000189781189},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.659600019454956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6359000205993652},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6176999807357788},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5974000096321106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5703999996185303},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5404999852180481},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5278000235557556},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.498199999332428},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C131720326","wikidata":"https://www.wikidata.org/wiki/Q5196075","display_name":"Curvelet","level":4,"score":0.4203999936580658},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4101000130176544},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2962000072002411},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.28360000252723694},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.26499998569488525}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754959","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7752844734","display_name":null,"funder_award_id":"62162003","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":22,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2340897893","https://openalex.org/W2963789515","https://openalex.org/W2982770724","https://openalex.org/W2985406498","https://openalex.org/W3035175896","https://openalex.org/W3035564946","https://openalex.org/W3035574168","https://openalex.org/W3092609815","https://openalex.org/W3133542152","https://openalex.org/W3169708801","https://openalex.org/W3172854222","https://openalex.org/W3175956495","https://openalex.org/W4289639938","https://openalex.org/W4312792979","https://openalex.org/W4312933868","https://openalex.org/W4327852039","https://openalex.org/W4386072096","https://openalex.org/W4387704395","https://openalex.org/W4390873054","https://openalex.org/W4394597085","https://openalex.org/W4402754201"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"latent":[1],"diffusion":[2,86],"models":[3],"(LDMs)":[4],"have":[5],"been":[6],"explored":[7],"to":[8,56,63,83,88,112,165],"generate":[9,89],"diverse":[10,90],"domain-specific":[11,91],"images":[12,29,92,118,176],"based":[13],"on":[14,202],"source":[15,109,127,189],"domain":[16,22,64,110,190],"data,":[17],"showing":[18],"promising":[19],"performance":[20],"in":[21,66,115,177,212],"generalization":[23,65],"tasks.":[24],"However,":[25],"although":[26],"the":[27,35,40,46,71,85,95,121,125,137,141,159,167],"generated":[28,142,160,187],"present":[30],"counterfactual":[31,133],"augmentation,":[32,134],"such":[33,49],"as":[34,50],"background":[36],"and":[37,52,144,157,188],"style":[38],"changes,":[39],"distortion":[41],"of":[42,124,140,170,175],"object":[43,67,96,138,152,215],"details":[44,153],"disrupts":[45],"causal":[47],"factors,":[48],"texture":[51],"shape.":[53],"This":[54,149],"leads":[55],"negative":[57],"outcomes":[58],"when":[59],"directly":[60],"applying":[61],"LDM":[62,114],"detection.":[68,216],"To":[69],"address":[70],"problems":[72],"mentioned":[73],"above,":[74],"we":[75,99,130,179],"propose":[76,131],"Object-Preserving":[77],"Counterfactual":[78],"Diffusion":[79],"augmentation":[80],"method":[81],"(OPCD)":[82],"explore":[84],"model":[87],"without":[93],"disrupting":[94],"details.":[97],"First,":[98],"construct":[100],"a":[101,172,181],"region-aware":[102],"image":[103,143],"generation":[104],"framework,":[105],"which":[106,135],"leverages":[107],"labeled":[108],"data":[111],"guide":[113],"generating":[116,171],"region-constrained":[117],"that":[119,151,158,207],"preserve":[120],"semantic":[122],"consistency":[123],"original":[126],"images.":[128],"Second,":[129],"object-preserving":[132],"retains":[136],"region":[139],"fuses":[145],"diversified":[146],"global":[147],"information.":[148],"ensures":[150],"are":[154],"not":[155],"distorted":[156],"information":[161],"is":[162],"maintained.":[163],"Third,":[164],"reduce":[166],"resource":[168],"burden":[169],"large":[173],"number":[174],"LDM,":[178],"design":[180],"random":[182],"insertion":[183],"strategy.":[184],"It":[185],"mixes":[186],"images,":[191],"turning":[192],"limited":[193],"diversity":[194],"samples":[195],"into":[196],"abundant":[197],"training":[198],"data.":[199],"Experimental":[200],"results":[201],"several":[203],"benchmark":[204],"datasets":[205],"show":[206],"OPCD":[208],"outperforms":[209],"existing":[210],"methods":[211],"single-domain":[213],"generalized":[214],"Codes":[217],"can":[218],"be":[219],"found":[220],"at":[221],"https://github.com/qinhongda8/OPCD.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}