{"id":"https://openalex.org/W7128818896","doi":"https://doi.org/10.1109/tpami.2026.3664388","title":"Penny-Wise and Pound-Foolish in AI-Generated Image Detection","display_name":"Penny-Wise and Pound-Foolish in AI-Generated Image Detection","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7128818896","doi":"https://doi.org/10.1109/tpami.2026.3664388","pmid":"https://pubmed.ncbi.nlm.nih.gov/41686675"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3664388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3664388","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":"Yabin Wang","orcid":"https://orcid.org/0000-0003-2931-572X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabin Wang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-2931-572X","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038918043","display_name":"Zhiwu Huang","orcid":"https://orcid.org/0000-0002-7385-079X"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhiwu Huang","raw_affiliation_strings":["University of Southampton, Southampton, U.K"],"raw_orcid":"https://orcid.org/0000-0002-7385-079X","affiliations":[{"raw_affiliation_string":"University of Southampton, Southampton, U.K","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou Su","orcid":"https://orcid.org/0000-0002-6518-3130"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Su","raw_affiliation_strings":["Xi’an Jiaotong University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-6518-3130","affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University, Xi’an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107178996","display_name":"Adam Prugel-Bennett","orcid":null},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adam Pr\u00fcgel-Bennett","raw_affiliation_strings":["University of Southampton, Southampton, U.K"],"raw_orcid":"https://orcid.org/0000-0002-1329-5077","affiliations":[{"raw_affiliation_string":"University of Southampton, Southampton, U.K","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125996683","display_name":"Xiaopeng Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Hong","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-0611-0636","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.1051,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96835555,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"48","issue":"7","first_page":"7707","last_page":"7719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.3131999969482422,"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":0.3131999969482422,"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":0.1534000039100647,"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":0.14409999549388885,"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/generalization","display_name":"Generalization","score":0.8324000239372253},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7003999948501587},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6965000033378601},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5999000072479248},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5139999985694885},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5088000297546387},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4235000014305115},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.388700008392334},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37470000982284546}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8324000239372253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444999814033508},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7003999948501587},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6965000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6758000254631042},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5400000214576721},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5088000297546387},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4235000014305115},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.388700008392334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.31139999628067017},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3068999946117401},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C2776973144","wikidata":"https://www.wikidata.org/wiki/Q6880649","display_name":"Misuse detection","level":4,"score":0.27149999141693115},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.26420000195503235},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3664388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3664388","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41686675","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41686675","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1274369146","display_name":null,"funder_award_id":"202306280130","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G3048430866","display_name":null,"funder_award_id":"62376070","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4935473288","display_name":null,"funder_award_id":"62076195","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320277","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2473930607","https://openalex.org/W2531409750","https://openalex.org/W2560647685","https://openalex.org/W2891145043","https://openalex.org/W2909336075","https://openalex.org/W2963684180","https://openalex.org/W2963720850","https://openalex.org/W2982058372","https://openalex.org/W2991318208","https://openalex.org/W3019200173","https://openalex.org/W3034196597","https://openalex.org/W3034577585","https://openalex.org/W3034713808","https://openalex.org/W3034795015","https://openalex.org/W3035063907","https://openalex.org/W3037492894","https://openalex.org/W3173581984","https://openalex.org/W3174770825","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W4205991051","https://openalex.org/W4292793883","https://openalex.org/W4308234128","https://openalex.org/W4312310776","https://openalex.org/W4312651322","https://openalex.org/W4312753047","https://openalex.org/W4312933868","https://openalex.org/W4313127140","https://openalex.org/W4313189772","https://openalex.org/W4319300674","https://openalex.org/W4385815563","https://openalex.org/W4386071547","https://openalex.org/W4386071953","https://openalex.org/W4386075856","https://openalex.org/W4386075954","https://openalex.org/W4386187806","https://openalex.org/W4388858946","https://openalex.org/W4390871965","https://openalex.org/W4390872773","https://openalex.org/W4390873235","https://openalex.org/W4391092975","https://openalex.org/W4392623241","https://openalex.org/W4393154086","https://openalex.org/W4394597038","https://openalex.org/W4399418483","https://openalex.org/W4402716164","https://openalex.org/W4405229107","https://openalex.org/W4410706528","https://openalex.org/W4413145584","https://openalex.org/W7133185348","https://openalex.org/W7133189282","https://openalex.org/W7133207408","https://openalex.org/W7133242127","https://openalex.org/W7133489722"],"related_works":[],"abstract_inverted_index":{"The":[0,174],"rise":[1],"of":[2,35,45,63,84,166,192,208],"AI-generated":[3,85,146,167,195],"images":[4],"has":[5],"sparked":[6],"serious":[7],"concerns":[8],"about":[9],"their":[10],"potential":[11],"misuse":[12],"across":[13,142],"various":[14],"domains,":[15],"prompting":[16],"the":[17,33,41,60,82,135,156,163],"urgent":[18],"need":[19],"for":[20,49,81,115,161],"robust":[21],"detection":[22,87,148,169,197],"methods.":[23],"Despite":[24],"advancements,":[25],"many":[26],"current":[27],"approaches":[28],"prioritize":[29],"short-term":[30,50],"gains":[31,51],"at":[32],"expense":[34],"long-term":[36,61],"effectiveness.":[37],"This":[38],"paper":[39],"critiques":[40],"overly":[42],"specialized":[43],"approach":[44],"fine-tuning":[46],"pre-trained":[47,90],"models":[48],"on":[52,88,124,210],"a":[53,76,89,95,100,125,188,205],"single":[54,126],"AI":[55,128],"image":[56,86,119,129,147,168,196],"dataset,":[57,130],"while":[58,112,203],"disregarding":[59],"imperative":[62],"achieving":[64,187],"generalization":[65,83,114,164,183],"and":[66,99],"knowledge":[67,106,185],"retention.":[68],"To":[69],"address":[70],"this":[71],"trade-off":[72],"issue,":[73],"we":[74],"propose":[75],"novel":[77],"learning":[78],"framework":[79],"(PoundNet)":[80],"vision-language":[91],"model.":[92],"PoundNet":[93,123,180],"incorporates":[94],"learnable":[96],"prompt":[97],"design":[98],"balanced":[101],"objective":[102],"to":[103,171,200],"preserve":[104],"broad":[105],"from":[107],"upstream":[108],"tasks":[109,117],"(object":[110],"classification)":[111],"enhancing":[113],"downstream":[116],"(AI-generated":[118],"detection).":[120],"We":[121,137],"train":[122],"standard":[127],"following":[131],"common":[132],"practice":[133],"in":[134,194],"literature.":[136],"then":[138],"evaluate":[139],"its":[140],"performance":[141,198,207],"10":[143],"large-scale":[144],"public":[145],"datasets":[149],"with":[150,184],"5":[151],"main":[152],"evaluation":[153,177],"metrics,":[154],"forming":[155],"largest":[157],"benchmark":[158,176],"test":[159],"set":[160],"assessing":[162],"ability":[165],"models,":[170],"our":[172],"knowledge.":[173],"comprehensive":[175],"demonstrates":[178],"that":[179],"successfully":[181],"balances":[182],"retention,":[186],"remarkable":[189],"relative":[190],"improvement":[191],"19%":[193],"compared":[199],"state-of-the-art":[201],"methods,":[202],"maintaining":[204],"strong":[206],"63%":[209],"object":[211],"classification":[212],"tasks.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-07T06:13:29.825681","created_date":"2026-02-14T00:00:00"}