{"id":"https://openalex.org/W7162011903","doi":"https://doi.org/10.48550/arxiv.2605.21207","title":"PGC: Peak-Guided Calibration for Generalizable AI-Generated Image Detection","display_name":"PGC: Peak-Guided Calibration for Generalizable AI-Generated Image Detection","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162011903","doi":"https://doi.org/10.48550/arxiv.2605.21207"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21207","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21207","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.21207","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136700797","display_name":"Xiaoyu Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136694484","display_name":"Jianwei Fei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei, Jianwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136722637","display_name":"Peipeng Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Peipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136648426","display_name":"Jingchang Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Jingchang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136704178","display_name":"Chong Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Chong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136677160","display_name":"Zhihua Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Zhihua","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5593000054359436,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5593000054359436,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11909999698400497,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.10819999873638153,"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/discriminative-model","display_name":"Discriminative model","score":0.8342000246047974},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6776999831199646},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6639999747276306},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6114000082015991},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5429999828338623},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48919999599456787},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.46950000524520874},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4514000117778778}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8342000246047974},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6776999831199646},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6639999747276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.663100004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6450999975204468},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48919999599456787},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.46950000524520874},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4244999885559082},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3476000130176544},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.34139999747276306},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3025999963283539},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21207","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21207","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.21207","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21207","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7427572011947632,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"evolution":[2],"of":[3,37],"generative":[4],"AI,":[5],"from":[6,123],"GANs":[7],"to":[8,88,108],"modern":[9],"diffusion":[10],"models,":[11],"has":[12],"resulted":[13],"in":[14,103],"increasingly":[15],"subtle":[16,96],"discriminative":[17,80],"clues.":[18],"These":[19],"fine-grained":[20],"signals":[21,87],"are":[22],"often":[23],"overshadowed":[24],"by":[25,71,140],"dominant,":[26],"high-fidelity":[27],"image":[28],"content":[29],"(e.g.,":[30],"the":[31,35,52,78,90,104,115],"main":[32],"subject),":[33],"limiting":[34],"reliability":[36],"existing":[38],"detectors":[39],"that":[40,62,76,98,130],"predominantly":[41],"rely":[42],"on":[43,142,150],"global":[44,91,105],"representations.":[45],"To":[46],"address":[47],"this":[48],"challenge,":[49],"we":[50,113],"propose":[51],"Peak-Guided":[53],"Calibration":[54],"(PGC)":[55],"framework.":[56],"PGC":[57,83,131],"introduces":[58],"a":[59,67,73,118],"novel":[60],"strategy":[61],"aggregates":[63],"salient":[64],"features":[65],"via":[66],"peak-focusing":[68],"mechanism.":[69],"Specifically,":[70,135],"employing":[72],"peak-sensitive":[74],"aggregation":[75],"accentuates":[77],"most":[79],"local":[81],"clues,":[82],"leverages":[84],"these":[85],"critical":[86],"calibrate":[89],"decision.":[92],"This":[93],"approach":[94],"recovers":[95],"patterns":[97],"would":[99],"otherwise":[100],"be":[101],"submerged":[102],"context.":[106],"Furthermore,":[107],"better":[109],"simulate":[110],"real-world":[111],"threats,":[112],"introduce":[114],"CommGen15":[116,144],"dataset,":[117,145],"challenging":[119],"benchmark":[120],"comprising":[121],"samples":[122],"15":[124],"commercial":[125],"models.":[126],"Extensive":[127],"experiments":[128],"demonstrate":[129],"achieves":[132],"state-of-the-art":[133],"performance.":[134],"it":[136],"improves":[137],"mean":[138],"accuracy":[139],"+12.3%":[141],"our":[143],"and":[146,158],"sets":[147],"new":[148],"records":[149],"standard":[151],"benchmarks,":[152],"including":[153],"GenImage":[154],"(+2.1%),":[155],"AIGI":[156],"(+3.5%),":[157],"UniversalFakeDetect":[159],"(+1.7%).":[160],"Code":[161],"is":[162],"available":[163],"at":[164],"https://github.com/xiaoyu6868/PGC.":[165]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-22T00:00:00"}