{"id":"https://openalex.org/W7155499581","doi":"https://doi.org/10.48550/arxiv.2604.21478","title":"Rethinking Cross-Domain Evaluation for Face Forgery Detection with Semantic Fine-grained Alignment and Mixture-of-Experts","display_name":"Rethinking Cross-Domain Evaluation for Face Forgery Detection with Semantic Fine-grained Alignment and Mixture-of-Experts","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155499581","doi":"https://doi.org/10.48550/arxiv.2604.21478"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.21478","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21478","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.2604.21478","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134500539","display_name":"Yuhan Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yuhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134471410","display_name":"Tao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134497681","display_name":"Decheng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Decheng","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5113000273704529,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5113000273704529,"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/T11448","display_name":"Face recognition and analysis","score":0.2761000096797943,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.053599998354911804,"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/robustness","display_name":"Robustness (evolution)","score":0.7522000074386597},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6510000228881836},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5127000212669373},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5123000144958496},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.4293000102043152},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4117000102996826},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.3937999904155731},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3871000111103058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544000148773193},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7522000074386597},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6510000228881836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.613099992275238},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46380001306533813},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.4293000102043152},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3822999894618988},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.21478","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21478","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.2604.21478","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21478","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":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.45334407687187195}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Nowadays,":[0],"visual":[1],"data":[2,71],"forgery":[3,24,174],"detection":[4,65],"plays":[5],"an":[6,61,82,125],"increasingly":[7],"important":[8,62],"role":[9],"in":[10],"social":[11],"and":[12,139,156,178],"economic":[13],"security":[14],"with":[15,99,194,198],"the":[16,47,52,117,133,157,182,187,195],"rapid":[17],"development":[18],"of":[19,32,49,143],"generative":[20],"models.":[21],"Existing":[22],"face":[23],"detectors":[25,115],"still":[26],"can't":[27],"achieve":[28],"satisfactory":[29],"performance":[30,122,192],"because":[31],"poor":[33],"generalization":[34],"ability":[35],"across":[36,70,89],"datasets.":[37],"The":[38],"key":[39],"factor":[40],"that":[41,85,112,149,186],"led":[42],"to":[43,59,110,153,169],"this":[44],"phenomenon":[45],"is":[46,108],"lack":[48],"suitable":[50,200],"metrics:":[51],"commonly":[53],"used":[54],"cross-dataset":[55],"AUC":[56,88],"metric":[57,84,119],"fails":[58],"reveal":[60],"issue":[63],"where":[64],"scores":[66],"may":[67],"shift":[68],"significantly":[69],"domains.":[72],"To":[73],"explicitly":[74],"evaluate":[75],"cross-domain":[76],"score":[77],"comparability,":[78],"we":[79,130],"propose":[80,132],"\\textbf{Cross-AUC},":[81],"evaluation":[83],"can":[86],"compute":[87],"dataset":[90,98],"pairs":[91],"by":[92],"contrasting":[93],"real":[94],"samples":[95,101],"from":[96,102,165],"one":[97],"fake":[100],"another":[103],"(and":[104],"vice":[105],"versa).":[106],"It":[107],"interesting":[109],"find":[111],"evaluating":[113],"representative":[114],"under":[116],"Cross-AUC":[118],"reveals":[120],"substantial":[121],"drops,":[123],"exposing":[124],"overlooked":[126],"robustness":[127],"problem.":[128],"Besides,":[129],"also":[131],"novel":[134],"framework":[135],"\\textbf{S}emantic":[136],"\\textbf{F}ine-grained":[137],"\\textbf{A}lignment":[138],"\\textbf{M}ixture-of-Experts":[140],"(\\textbf{SFAM}),":[141],"consisting":[142],"a":[144],"patch-level":[145],"image-text":[146],"alignment":[147],"module":[148],"enhances":[150],"CLIP's":[151],"sensitivity":[152],"manipulation":[154],"artifacts,":[155],"facial":[158,167],"region":[159],"mixture-of-experts":[160],"module,":[161],"which":[162],"routes":[163],"features":[164],"different":[166],"regions":[168],"specialized":[170],"experts":[171],"for":[172],"region-aware":[173],"analysis.":[175],"Extensive":[176],"qualitative":[177],"quantitative":[179],"experiments":[180],"on":[181],"public":[183],"datasets":[184],"prove":[185],"proposed":[188],"method":[189],"achieves":[190],"superior":[191],"compared":[193],"state-of-the-art":[196],"methods":[197],"various":[199],"metrics.":[201]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-25T00:00:00"}