{"id":"https://openalex.org/W4414545442","doi":"https://doi.org/10.32604/cmc.2025.069482","title":"CAFE-GAN: CLIP-Projected GAN with Attention-Aware Generation and Multi-Scale Discrimination","display_name":"CAFE-GAN: CLIP-Projected GAN with Attention-Aware Generation and Multi-Scale Discrimination","publication_year":2025,"publication_date":"2025-09-26","ids":{"openalex":"https://openalex.org/W4414545442","doi":"https://doi.org/10.32604/cmc.2025.069482"},"language":"en","primary_location":{"id":"doi:10.32604/cmc.2025.069482","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.069482","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.32604/cmc.2025.069482","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031804796","display_name":"Xuanhong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanhong Wang","raw_affiliation_strings":["School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101037059","display_name":"Hongyu Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Guo","raw_affiliation_strings":["School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014516371","display_name":"Jiazhen Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazhen Li","raw_affiliation_strings":["School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089257569","display_name":"Mingchen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingchen Wang","raw_affiliation_strings":["School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352422","display_name":"Xian Wang","orcid":"https://orcid.org/0000-0003-4113-8084"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Wang","raw_affiliation_strings":["School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100376292","display_name":"Yijun Zhang","orcid":"https://orcid.org/0000-0001-8820-2552"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijun Zhang","raw_affiliation_strings":["School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Xi\u2019an University of Posts and Telecomunications, Xi\u2019an, 710121, China 2 Test Center, National University of Defense Technology, Xi\u2019an, 710106, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210136859"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29167017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"86","issue":"1","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.7777000069618225,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.7777000069618225,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.7458999752998352,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.6744999885559082,"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/discriminator","display_name":"Discriminator","score":0.8359000086784363},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5745000243186951},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.554099977016449},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5267000198364258},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5202000141143799},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5034000277519226},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.47909998893737793},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.44670000672340393}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8359000086784363},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430999875068665},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.554099977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5509999990463257},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5267000198364258},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5202000141143799},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.296099990606308},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2851000130176544},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.32604/cmc.2025.069482","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.069482","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.32604/cmc.2025.069482","is_oa":true,"landing_page_url":"https://doi.org/10.32604/cmc.2025.069482","pdf_url":null,"source":{"id":"https://openalex.org/S4210191605","display_name":"Computers, materials & continua/Computers, materials & continua (Print)","issn_l":"1546-2218","issn":["1546-2218","1546-2226"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers, Materials & Continua","raw_type":"journal-article"},"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":{"Over":[0],"the":[1,11,73,92,101,131,169],"past":[2],"decade,":[3],"large-scale":[4],"pre-trained":[5,56,113],"autoregressive":[6],"and":[7,23,25,33,50,79,116,126,133,151,158,166,171],"diffusion":[8],"models":[9,19,179],"rejuvenated":[10],"field":[12],"of":[13,164],"text-guided":[14],"image":[15],"generation.":[16],"However,":[17],"these":[18,39],"require":[20],"enormous":[21],"datasets":[22,135],"parameters,":[24],"their":[26],"multi-step":[27],"generation":[28,142],"processes":[29],"are":[30],"often":[31],"inefficient":[32],"difficult":[34],"to":[35,75],"control.":[36],"To":[37],"address":[38],"challenges,":[40],"we":[41,66,84,106],"propose":[42],"CAFE-GAN,":[43],"a":[44,55,68,86,108,118],"CLIP-Projected":[45],"GAN":[46],"with":[47,60,100,154,161],"Attention-Aware":[48],"Generation":[49],"Multi-Scale":[51],"Discrimination,":[52],"which":[53,96],"incorporates":[54],"CLIP":[57,93],"model":[58],"along":[59],"several":[61],"key":[62],"architectural":[63],"innovations.":[64],"First,":[65],"embed":[67],"coordinate":[69],"attention":[70],"mechanism":[71],"into":[72],"generator":[74],"capture":[76],"long-range":[77],"dependencies":[78],"enhance":[80],"feature":[81,119],"representation.":[82],"Second,":[83],"introduce":[85],"trainable":[87],"linear":[88],"projection":[89],"layer":[90],"after":[91],"text":[94],"encoder,":[95],"aligns":[97],"textual":[98],"embeddings":[99],"generator\u2019s":[102],"semantic":[103,159],"space.":[104],"Third,":[105],"design":[107],"multi-scale":[109],"discriminator":[110],"that":[111,137],"leverages":[112],"visual":[114,156],"features":[115],"integrates":[117],"regularization":[120],"strategy,":[121],"thereby":[122],"improving":[123],"training":[124],"stability":[125],"discrimination":[127],"performance.":[128],"Experiments":[129],"on":[130,168,191],"CUB":[132,170],"COCO":[134,172],"demonstrate":[136],"CAFE-GAN":[138],"outperforms":[139],"existing":[140],"text-to-image":[141,178,194],"methods,":[143],"achieving":[144],"lower":[145],"Fr\u00e9chet":[146],"Inception":[147],"Distance":[148],"(FID)":[149],"scores":[150,163],"generating":[152],"images":[153],"superior":[155],"quality":[157],"fidelity,":[160],"FID":[162],"9.84":[165],"5.62":[167],"datasets,":[173],"respectively,":[174],"surpassing":[175],"current":[176],"state-of-the-art":[177],"by":[180],"varying":[181],"degrees.":[182],"These":[183],"findings":[184],"offer":[185],"valuable":[186],"insights":[187],"for":[188],"future":[189],"research":[190],"efficient,":[192],"controllable":[193],"synthesis.":[195]},"counts_by_year":[],"updated_date":"2026-06-25T06:16:34.145877","created_date":"2025-10-10T00:00:00"}