{"id":"https://openalex.org/W4412494052","doi":"https://doi.org/10.1109/tnnls.2025.3584554","title":"RealignDiff: Boosting Text-to-Image Diffusion Model With Coarse-to-Fine Semantic Realignment","display_name":"RealignDiff: Boosting Text-to-Image Diffusion Model With Coarse-to-Fine Semantic Realignment","publication_year":2025,"publication_date":"2025-07-18","ids":{"openalex":"https://openalex.org/W4412494052","doi":"https://doi.org/10.1109/tnnls.2025.3584554","pmid":"https://pubmed.ncbi.nlm.nih.gov/40679886"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3584554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3584554","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","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":"https://openalex.org/A5101692928","display_name":"Zutao Jiang","orcid":"https://orcid.org/0000-0002-6787-5499"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zutao Jiang","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102519401","display_name":"Guian Fang","orcid":"https://orcid.org/0009-0004-7344-2333"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guian Fang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100297958","display_name":"Jianhua Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jianhua Han","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003878191","display_name":"Guansong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Guansong Lu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030497493","display_name":"Songcen Xu","orcid":"https://orcid.org/0000-0002-0022-0906"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Hang Xu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019092879","display_name":"Shengcai Liao","orcid":"https://orcid.org/0000-0001-8941-2295"},"institutions":[{"id":"https://openalex.org/I201726411","display_name":"United Arab Emirates University","ror":"https://ror.org/01km6p862","country_code":"AE","type":"education","lineage":["https://openalex.org/I201726411"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Shengcai Liao","raw_affiliation_strings":["College of Information Technology, United Arab Emirates University, Al Ain, United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"College of Information Technology, United Arab Emirates University, Al Ain, United Arab Emirates","institution_ids":["https://openalex.org/I201726411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, School of Intelligent Engineering, Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, School of Intelligent Engineering, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101692928"],"corresponding_institution_ids":["https://openalex.org/I4210136793"],"apc_list":null,"apc_paid":null,"fwci":4.7137,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94770935,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"36","issue":"10","first_page":"19010","last_page":"19023"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.8080999851226807,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.8080999851226807,"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/T10028","display_name":"Topic Modeling","score":0.7979000210762024,"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/T10862","display_name":"AI in cancer detection","score":0.7746999859809875,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.797279953956604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.560380220413208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4810345768928528},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4064546823501587},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32101479172706604}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.797279953956604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.560380220413208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4810345768928528},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4064546823501587},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32101479172706604}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3584554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3584554","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40679886","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40679886","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 neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G246423351","display_name":null,"funder_award_id":"PCL2024A04","funder_id":"https://openalex.org/F4320318558","funder_display_name":"Peng Cheng Laboratory"},{"id":"https://openalex.org/G3569708910","display_name":null,"funder_award_id":"2024B0101010003","funder_id":"https://openalex.org/F4320324202","funder_display_name":"Guangdong Science and Technology Department"}],"funders":[{"id":"https://openalex.org/F4320318558","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06"},{"id":"https://openalex.org/F4320324202","display_name":"Guangdong Science and Technology Department","ror":"https://ror.org/00tjzgn92"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W2963163163","https://openalex.org/W2963966654","https://openalex.org/W2964313012","https://openalex.org/W2966792645","https://openalex.org/W3153469116","https://openalex.org/W3180355996","https://openalex.org/W4224281861","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4312974539","https://openalex.org/W4385245566","https://openalex.org/W4386075639","https://openalex.org/W4386076458","https://openalex.org/W4390872325","https://openalex.org/W4390872671","https://openalex.org/W4390874002","https://openalex.org/W4390874566","https://openalex.org/W4402917081","https://openalex.org/W4404101422","https://openalex.org/W4404612908","https://openalex.org/W4404624946","https://openalex.org/W4411245279"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2147697413","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,10,24,36,61,152],"text-to-image":[3,62],"diffusion":[4,63],"models":[5],"have":[6,21],"achieved":[7],"remarkable":[8],"success":[9],"generating":[11],"high-quality,":[12],"realistic":[13],"images":[14,60,120],"from":[15,121],"textual":[16,33],"descriptions.":[17],"However,":[18],"these":[19],"approaches":[20],"faced":[22],"challenges":[23],"precisely":[25],"aligning":[26],"the":[27,32,37,55,66,76,83,87,92,97,117,129,136,160],"generated":[28,88,119],"visual":[29,154],"content":[30],"with":[31,159],"concepts":[34],"described":[35],"prompts.":[38],"In":[39,65],"this":[40],"article,":[41],"we":[42],"propose":[43],"a":[44,71,103,110,122,149],"two-stage":[45,138],"coarse-to-fine":[46,139],"semantic":[47,68,84,99,124,140,157],"realignment":[48,69,100,141,146],"method,":[49],"named":[50],"RealignDiff,":[51],"aimed":[52],"at":[53],"improving":[54],"alignment":[56],"between":[57,86],"text":[58,94],"and":[59,91,109,131,156],"models.":[64],"coarse":[67],"phase,":[70],"novel":[72],"caption":[73,90,106],"reward,":[74],"leveraging":[75],"BLIP-2":[77],"model,":[78],"is":[79],"proposed":[80,137],"to":[81,115],"evaluate":[82],"discrepancy":[85],"image":[89],"given":[93],"prompt.":[95,162],"Subsequently,":[96],"fine":[98],"stage":[101],"uses":[102],"local":[104,123],"dense":[105],"generation":[107],"module":[108,114],"reweighting":[111],"attention":[112],"modulation":[113],"refine":[116],"previously":[118],"view.":[125],"Experimental":[126],"results":[127],"on":[128],"MS-COCO":[130],"ViLG-300":[132],"datasets":[133],"demonstrate":[134],"that":[135],"method":[142],"outperforms":[143],"other":[144],"baseline":[145],"techniques":[147],"by":[148],"substantial":[150],"margin":[151],"both":[153],"quality":[155],"similarity":[158],"input":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}