{"id":"https://openalex.org/W7118208389","doi":"https://doi.org/10.1109/tmm.2026.3651067","title":"Generalizable and Adaptive Continual Learning Framework for AI-Generated Image Detection","display_name":"Generalizable and Adaptive Continual Learning Framework for AI-Generated Image Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7118208389","doi":"https://doi.org/10.1109/tmm.2026.3651067"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651067","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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":null,"display_name":"Hanyi Wang","orcid":"https://orcid.org/0000-0003-1899-6750"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyi Wang","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1899-6750","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121970786","display_name":"Jun Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Lan","raw_affiliation_strings":["Antgroup, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Antgroup, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111170491","display_name":"Yaoyu Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoyu Kang","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110390049","display_name":"Huijia Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huijia Zhu","raw_affiliation_strings":["Antgroup, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Antgroup, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080477405","display_name":"Weiqiang Wang","orcid":"https://orcid.org/0000-0002-6159-619X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiqiang Wang","raw_affiliation_strings":["Antgroup, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6159-619X","affiliations":[{"raw_affiliation_string":"Antgroup, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070962435","display_name":"Zhuosheng Zhang","orcid":"https://orcid.org/0000-0002-4183-3645"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuosheng Zhang","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4183-3645","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shilin Wang","orcid":"https://orcid.org/0000-0002-8214-6809"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilin Wang","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8214-6809","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"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":0.03553695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"2693","last_page":"2704"},"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":0.3555000126361847,"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":0.3555000126361847,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.3061999976634979,"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":0.06920000165700912,"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/leverage","display_name":"Leverage (statistics)","score":0.7070000171661377},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5583000183105469},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5123000144958496},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.47360000014305115},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.3978999853134155},{"id":"https://openalex.org/keywords/data-driven","display_name":"Data-driven","score":0.3749000132083893},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3508000075817108},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.33149999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8210999965667725},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7070000171661377},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6366999745368958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6186000108718872},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5583000183105469},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.47360000014305115},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.33149999380111694},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3091999888420105},{"id":"https://openalex.org/C171836373","wikidata":"https://www.wikidata.org/wiki/Q2266329","display_name":"Linear interpolation","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28540000319480896},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651067","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46824946999549866}],"awards":[{"id":"https://openalex.org/G5950341906","display_name":null,"funder_award_id":"62271307","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"malicious":[1],"misuse":[2],"and":[3,30,121,147,172,189],"widespread":[4],"dissemination":[5],"of":[6,16,34,117,182,218,230],"AI-generated":[7],"images":[8],"pose":[9],"a":[10,58,79,86,107,126,156,179],"significant":[11],"threat":[12],"to":[13,24,26,69,84,143,195,198],"the":[14,31,74,99,137,145,152,211],"authenticity":[15],"online":[17],"information.":[18],"Current":[19],"detection":[20,43,89],"methods":[21],"often":[22],"struggle":[23],"generalize":[25],"unseen":[27,103],"generative":[28,35,71,170,184],"models,":[29,185,191],"rapid":[32],"evolution":[33],"techniques":[36],"continuously":[37],"exacerbates":[38],"this":[39,53,97],"challenge.":[40],"Without":[41],"adaptability,":[42],"models":[44,120,171],"risk":[45],"becoming":[46],"ineffective":[47],"in":[48,216],"real-world":[49,200],"applications.":[50],"To":[51,111],"address":[52],"critical":[54],"issue,":[55],"we":[56,77,124,135],"propose":[57],"novel":[59,118],"three-stage":[60],"domain":[61],"continual":[62,108,223],"learning":[63,109,224],"framework":[64],"designed":[65],"for":[66],"continuous":[67],"adaptation":[68],"evolving":[70],"models.":[72],"In":[73],"first":[75],"stage,":[76],"employ":[78],"strategic":[80],"parameter-efficient":[81],"fine-tuning":[82],"approach":[83],"develop":[85],"transferable":[87],"offline":[88,208],"model":[90],"with":[91,130],"strong":[92],"generalization":[93],"capabilities.":[94],"Building":[95],"upon":[96],"foundation,":[98],"second":[100],"stage":[101,154],"integrates":[102],"data":[104,127],"streams":[105],"into":[106],"process.":[110],"efficiently":[112],"learn":[113],"from":[114],"limited":[115],"samples":[116],"generated":[119],"mitigate":[122],"overfitting,":[123],"design":[125],"augmentation":[128],"chain":[129],"progressively":[131],"increasing":[132],"complexity.":[133],"Furthermore,":[134],"leverage":[136],"Kronecker-Factored":[138],"Approximate":[139],"Curvature":[140],"(K-FAC)":[141],"method":[142],"approximate":[144],"Hessian":[146],"alleviate":[148],"catastrophic":[149],"forgetting.":[150],"Finally,":[151],"third":[153],"utilizes":[155],"linear":[157],"interpolation":[158],"strategy":[159,225],"based":[160],"on":[161],"Linear":[162],"Mode":[163],"Connectivity,":[164],"effectively":[165],"capturing":[166],"commonalities":[167],"across":[168],"diverse":[169],"further":[173],"enhancing":[174],"overall":[175],"performance.":[176],"We":[177],"establish":[178],"comprehensive":[180],"benchmark":[181],"27":[183],"including":[186],"GANs,":[187],"deepfakes,":[188],"diffusion":[190],"chronologically":[192],"structured":[193],"up":[194],"August":[196],"2024":[197],"simulate":[199],"scenarios.":[201],"Extensive":[202],"experiments":[203],"demonstrate":[204],"that":[205],"our":[206],"initial":[207],"detectors":[209],"surpass":[210],"leading":[212],"baseline":[213],"by":[214],"+5.51%":[215],"terms":[217],"mean":[219],"average":[220,228],"precision.":[221],"Our":[222],"achieves":[226],"an":[227],"accuracy":[229],"92.20%,":[231],"outperforming":[232],"state-of-the-art":[233],"methods.":[234]},"counts_by_year":[],"updated_date":"2026-04-18T05:59:34.339393","created_date":"2026-01-05T00:00:00"}