{"id":"https://openalex.org/W7151247866","doi":"https://doi.org/10.48550/arxiv.2604.03555","title":"HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild","display_name":"HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild","publication_year":2026,"publication_date":"2026-04-04","ids":{"openalex":"https://openalex.org/W7151247866","doi":"https://doi.org/10.48550/arxiv.2604.03555"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.03555","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03555","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.03555","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133068856","display_name":"Fei Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113405461","display_name":"Dagong Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Dagong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064996014","display_name":"Mufeng Yao","orcid":"https://orcid.org/0009-0008-5047-5158"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Mufeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133084534","display_name":"Xinlei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Xinlei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133114309","display_name":"Fengjun Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Fengjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.7979000210762024,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.7979000210762024,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.037300001829862595,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0364999994635582,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/robustness","display_name":"Robustness (evolution)","score":0.7468000054359436},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6270999908447266},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6033999919891357},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5911999940872192},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5738999843597412},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4645000100135803},{"id":"https://openalex.org/keywords/backbone-network","display_name":"Backbone network","score":0.4535999894142151},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4196999967098236},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4194999933242798}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7468000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6937999725341797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6746000051498413},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6270999908447266},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6033999919891357},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5911999940872192},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5738999843597412},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4645000100135803},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41130000352859497},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.35510000586509705},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C2780934415","wikidata":"https://www.wikidata.org/wiki/Q20997131","display_name":"Border Security","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3174000084400177},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.03555","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03555","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.03555","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03555","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Robust":[0,147],"detection":[1,69,166],"of":[2,15,63],"AI-generated":[3],"images":[4],"in":[5,143,151],"the":[6,12,144,152],"wild":[7],"remains":[8],"challenging":[9],"due":[10],"to":[11,36],"rapid":[13],"evolution":[14],"generative":[16],"models":[17],"and":[18,40,83,96,108,135,155],"varied":[19],"real-world":[20],"distortions.":[21],"We":[22],"argue":[23],"that":[24,41,66,131],"relying":[25],"on":[26,162],"a":[27,58,101,111,127],"single":[28],"training":[29,75],"regime,":[30],"resolution,":[31],"or":[32],"backbone":[33,84,115],"is":[34,47],"insufficient":[35],"handle":[37],"all":[38],"conditions,":[39],"structured":[42],"heterogeneity":[43],"across":[44],"these":[45],"dimensions":[46],"essential":[48],"for":[49,61,104,114],"robust":[50],"detection.":[51],"To":[52],"this":[53],"end,":[54],"we":[55],"propose":[56],"HEDGE,":[57],"Heterogeneous":[59],"Ensemble":[60],"Detection":[62,150],"AI-GEnerated":[64],"images,":[65],"introduces":[67],"complementary":[68],"routes":[70],"along":[71],"three":[72],"axes:":[73],"diverse":[74],"data":[76,94],"with":[77,159],"strong":[78,160],"augmentation,":[79],"multi-scale":[80],"feature":[81],"extraction,":[82],"heterogeneity.":[85],"Specifically,":[86],"Route~A":[87],"progressively":[88],"constructs":[89],"DINOv3-based":[90],"detectors":[91],"through":[92],"staged":[93],"expansion":[95],"augmentation":[97],"escalation,":[98],"Route~B":[99],"incorporates":[100],"higher-resolution":[102],"branch":[103,113],"fine-grained":[105],"forensic":[106],"cues,":[107],"Route~C":[109],"adds":[110],"MetaCLIP2-based":[112],"diversity.":[116],"All":[117],"outputs":[118],"are":[119],"fused":[120],"via":[121],"logit-space":[122],"weighted":[123],"averaging,":[124],"refined":[125],"by":[126],"lightweight":[128],"dual-gating":[129],"mechanism":[130],"handles":[132],"branch-level":[133],"outliers":[134],"majority-dominated":[136],"fusion":[137],"errors.":[138],"HEDGE":[139],"achieves":[140],"4th":[141],"place":[142],"NTIRE":[145],"2026":[146],"AI-Generated":[148],"Image":[149],"Wild":[153],"Challenge":[154],"attains":[156],"state-of-the-art":[157],"performance":[158],"robustness":[161],"multiple":[163],"AIGC":[164],"image":[165],"benchmarks.":[167]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-08T00:00:00"}