{"id":"https://openalex.org/W4415539133","doi":"https://doi.org/10.1145/3746027.3754567","title":"Towards Good Generalizations for Diffusion Generated Image Detection Using Multiple Reconstruction Contrastive Learning","display_name":"Towards Good Generalizations for Diffusion Generated Image Detection Using Multiple Reconstruction Contrastive Learning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539133","doi":"https://doi.org/10.1145/3746027.3754567"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754567","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":"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/A5088627439","display_name":"Wanyi Zhuang","orcid":"https://orcid.org/0000-0001-9305-1189"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanyi Zhuang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9305-1189","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045938154","display_name":"Qi Chu","orcid":"https://orcid.org/0000-0003-3028-0755"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3028-0755","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114910706","display_name":"Tao Gong","orcid":"https://orcid.org/0000-0003-0026-6813"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Gong","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0026-6813","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077867418","display_name":"Changtao Miao","orcid":"https://orcid.org/0000-0002-7634-9992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changtao Miao","raw_affiliation_strings":["Independent, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7634-9992","affiliations":[{"raw_affiliation_string":"Independent, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064573190","display_name":"Nenghai Yu","orcid":"https://orcid.org/0000-0003-4417-9316"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenghai Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4417-9316","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32846122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5431","last_page":"5440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9972000122070312,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9972000122070312,"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/T11105","display_name":"Advanced Image Processing 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"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7876999974250793},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.641700029373169},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6324999928474426},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6164000034332275},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5496000051498413},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.48240000009536743},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.45100000500679016},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4212999939918518}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.79830002784729},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7876999974250793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6855999827384949},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.641700029373169},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6324999928474426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6164000034332275},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4300999939441681},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3206000030040741},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31139999628067017},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2630000114440918}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754567","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754567","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/G4318547390","display_name":null,"funder_award_id":"62472396,62121002","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":14,"referenced_works":["https://openalex.org/W2975558816","https://openalex.org/W2979259381","https://openalex.org/W3034577585","https://openalex.org/W3034795015","https://openalex.org/W3094728142","https://openalex.org/W4312388283","https://openalex.org/W4312443924","https://openalex.org/W4312933868","https://openalex.org/W4313476637","https://openalex.org/W4386071953","https://openalex.org/W4390873054","https://openalex.org/W4393154086","https://openalex.org/W4402716164","https://openalex.org/W4402753859"],"related_works":[],"abstract_inverted_index":{"A":[0],"striking":[1],"proficiency":[2],"of":[3,15,104,120,155,170],"diffusion":[4],"models":[5,54],"in":[6,81],"producing":[7],"and":[8,48,123,158],"manipulating":[9],"images":[10,122,157],"with":[11,112],"an":[12,42],"unprecedented":[13],"level":[14],"realism":[16],"has":[17],"unquestionably":[18],"elicited":[19],"concerns.":[20],"Many":[21],"methods":[22],"have":[23],"been":[24],"proposed":[25,172],"to":[26,100,115,137,151],"detect":[27],"generated":[28,105],"images.":[29],"In":[30,85,128],"particular,":[31],"recent":[32],"studies":[33],"reveal":[34],"that":[35],"autoencoder":[36,65],"reconstruction":[37,66,98,142,160],"error":[38,67],"can":[39],"serve":[40],"as":[41],"effective":[43],"indicator":[44],"for":[45,75],"distinguishing":[46],"authentic":[47],"synthetic":[49],"images,":[50],"since":[51],"most":[52],"generative":[53],"adopt":[55],"analogous":[56],"encoder-decoder":[57],"operation.":[58],"However,":[59],"the":[60,102,153,166,171],"reliance":[61],"on":[62],"a":[63,130,145],"single":[64],"provides":[68],"only":[69],"limited":[70],"information,":[71],"which":[72,95],"is":[73,135,149],"insufficient":[74],"comprehensively":[76],"capturing":[77],"discriminative":[78],"features,":[79],"resulting":[80],"restricted":[82],"generalization":[83,168],"performance.":[84],"this":[86],"paper,":[87],"we":[88],"propose":[89],"Multiple":[90],"Reconstruction":[91],"Contrastive":[92],"Learning":[93],"(MRCL),":[94],"leverages":[96],"multiple":[97,125,140],"residuals":[99],"enhance":[101],"generalizability":[103],"image":[106],"detection.":[107],"Specifically,":[108],"MRCL":[109],"applies":[110],"Dinov2-ViT":[111],"LoRA":[113],"fine-tuning":[114],"extract":[116],"fine-grained":[117],"feature":[118],"representations":[119],"origin":[121,156],"their":[124],"VAE":[126,141,159],"reconstructions.":[127],"addition,":[129],"Residual":[131],"Dense":[132],"Fusion":[133],"module":[134],"designed":[136],"effectively":[138],"combine":[139],"residuals.":[143],"Further,":[144],"contrastive":[146],"learning":[147],"strategy":[148],"adopted":[150],"guide":[152],"distance":[154],"representations.":[161],"Extensive":[162],"experimental":[163],"results":[164],"demonstrate":[165],"superior":[167],"performance":[169],"MRCL.":[173]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}