{"id":"https://openalex.org/W4405778570","doi":"https://doi.org/10.1109/access.2024.3522238","title":"Dual-Conditioned Training to Exploit Pre-Trained Codebook-Based Generative Model in Image Compression","display_name":"Dual-Conditioned Training to Exploit Pre-Trained Codebook-Based Generative Model in Image Compression","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4405778570","doi":"https://doi.org/10.1109/access.2024.3522238"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3522238","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3522238","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3522238","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024041814","display_name":"Shoma Iwai","orcid":"https://orcid.org/0000-0002-6340-3902"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shoma Iwai","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Sendai, Miyagi, Japan","Graduate School of Engineering, Tohoku University, Miyagi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6340-3902","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Sendai, Miyagi, Japan","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Miyagi, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009192524","display_name":"Tomo Miyazaki","orcid":"https://orcid.org/0000-0001-5205-0542"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomo Miyazaki","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Sendai, Miyagi, Japan","Graduate School of Engineering, Tohoku University, Miyagi, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5205-0542","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Sendai, Miyagi, Japan","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Miyagi, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020830042","display_name":"Shinichiro Omachi","orcid":"https://orcid.org/0000-0001-7706-9995"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinichiro Omachi","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Sendai, Miyagi, Japan","Graduate School of Engineering, Tohoku University, Miyagi, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7706-9995","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Sendai, Miyagi, Japan","institution_ids":["https://openalex.org/I201537933"]},{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Miyagi, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024041814"],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23016405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"198184","last_page":"198200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9929999709129333,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9929999709129333,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9832000136375427,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9714000225067139,"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/codebook","display_name":"Codebook","score":0.9115421175956726},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7736902832984924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7471041679382324},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.6430259346961975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5754598379135132},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5535564422607422},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.550940990447998},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5138804912567139},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4904053211212158},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.47553515434265137},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4196038246154785},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.397161602973938},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3831644654273987},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3502618670463562},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.318806916475296},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.06457766890525818}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.9115421175956726},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7736902832984924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7471041679382324},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.6430259346961975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5754598379135132},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5535564422607422},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.550940990447998},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5138804912567139},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4904053211212158},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.47553515434265137},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4196038246154785},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.397161602973938},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3831644654273987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3502618670463562},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.318806916475296},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.06457766890525818},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3522238","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3522238","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ae2823f8e72b4a289bae660517c829a0","is_oa":true,"landing_page_url":"https://doaj.org/article/ae2823f8e72b4a289bae660517c829a0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 198184-198200 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3522238","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3522238","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7024700476","display_name":null,"funder_award_id":"JP24KJ0343","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W2022805437","https://openalex.org/W2075577192","https://openalex.org/W2141089030","https://openalex.org/W2194775991","https://openalex.org/W2552465432","https://openalex.org/W2741137940","https://openalex.org/W2752796333","https://openalex.org/W2768814045","https://openalex.org/W2785562966","https://openalex.org/W2962785568","https://openalex.org/W2963073614","https://openalex.org/W2963814095","https://openalex.org/W2981613960","https://openalex.org/W2982853315","https://openalex.org/W3034469748","https://openalex.org/W3091266734","https://openalex.org/W3109585842","https://openalex.org/W3112587064","https://openalex.org/W3138516171","https://openalex.org/W3160589897","https://openalex.org/W3175457126","https://openalex.org/W3179468628","https://openalex.org/W3180355996","https://openalex.org/W3202918664","https://openalex.org/W4223425316","https://openalex.org/W4230291482","https://openalex.org/W4283831644","https://openalex.org/W4288083516","https://openalex.org/W4292256660","https://openalex.org/W4295682783","https://openalex.org/W4312388283","https://openalex.org/W4312806968","https://openalex.org/W4312933868","https://openalex.org/W4313021454","https://openalex.org/W4313120002","https://openalex.org/W4316660716","https://openalex.org/W4316830033","https://openalex.org/W4386065641","https://openalex.org/W4386075611","https://openalex.org/W4386076137","https://openalex.org/W4390871851","https://openalex.org/W4390872385","https://openalex.org/W4390874459","https://openalex.org/W4390874546","https://openalex.org/W4392739034","https://openalex.org/W4394625726","https://openalex.org/W4394625730","https://openalex.org/W4398164016","https://openalex.org/W4400770759","https://openalex.org/W4402727980","https://openalex.org/W4402754291","https://openalex.org/W4402952499","https://openalex.org/W4403841811","https://openalex.org/W4403878008","https://openalex.org/W6631190155","https://openalex.org/W6754634825","https://openalex.org/W6755487101","https://openalex.org/W6758867260","https://openalex.org/W6765779288","https://openalex.org/W6779823529","https://openalex.org/W6780365925","https://openalex.org/W6802517614","https://openalex.org/W6810067190","https://openalex.org/W6839082156","https://openalex.org/W6842542927","https://openalex.org/W6847426693","https://openalex.org/W6849095040","https://openalex.org/W6850224944","https://openalex.org/W6852953693","https://openalex.org/W6857419123","https://openalex.org/W6860885380"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W98470534","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071"],"abstract_inverted_index":{"Learned":[0],"image":[1,83],"compression":[2,77],"(LIC)":[3],"is":[4,67,135],"increasingly":[5],"gaining":[6],"attention.":[7],"To":[8],"improve":[9],"the":[10,99,106,120,144,150,165,167,172,199,204,220],"perceptual":[11],"quality":[12],"of":[13,223],"reconstructions,":[14],"generative":[15,21,30,52,59,240],"LIC":[16,31,53,241],"has":[17],"been":[18],"studied,":[19],"using":[20],"models":[22],"such":[23],"as":[24],"Generative":[25],"Adversarial":[26],"Networks":[27],"(GANs).":[28],"State-of-the-art":[29],"methods":[32,242],"have":[33],"achieved":[34],"remarkable":[35],"performance":[36],"even":[37],"in":[38,88,243],"low":[39],"bit":[40,152,174,210,227],"rate":[41,175],"settings.":[42],"Unlike":[43],"most":[44],"approaches":[45],"trained":[46],"from":[47,84],"scratch,":[48],"we":[49,141,158,197],"propose":[50,159],"a":[51,56,85,160],"that":[54,119,143],"utilizes":[55],"pre-trained":[57,100],"codebook-based":[58],"model,":[60],"Vector-Quantized":[61],"GAN":[62],"(VQGAN).":[63],"Specifically,":[64],"our":[65],"model":[66,168],"designed":[68],"to":[69,75,110,170,202,217],"exploit":[70,219],"its":[71],"powerful":[72],"image-generation":[73],"capabilities":[74],"enhance":[76],"performance.":[78,245],"Our":[79,115,229],"approach":[80],"reconstructs":[81],"an":[82],"transmitted":[86],"bitstream":[87],"two":[89,193],"steps:":[90],"(1)":[91],"estimating":[92],"VQGAN":[93,101,224],"tokens":[94],"and":[95,103,113,129,176,185],"feeding":[96],"them":[97],"into":[98],"decoder,":[102],"(2)":[104],"modifying":[105],"decoder\u2019s":[107],"intermediate":[108],"features":[109],"address":[111],"artifacts":[112],"distortions.":[114],"preliminary":[116],"experiments":[117],"reveal":[118],"information":[121,177],"allocation":[122,146,178],"between":[123,179],"<xref":[124,130,180,186],"ref-type=\"disp-formula\"":[125,131,181,187],"rid=\"deqn1\"":[126,182],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[127,133,183,189,252],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">(1)</xref>":[128,184],"rid=\"deqn2\"":[132,188],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">(2)</xref>":[134,190],"pivotal":[136],"for":[137,207],"reconstruction":[138],"quality.":[139],"Moreover,":[140],"found":[142],"ideal":[145],"varies":[147],"based":[148,191],"on":[149,192],"target":[151,209],"rate.":[153,211],"Motivated":[154],"by":[155],"these":[156],"findings,":[157],"novel":[161],"Dual-Conditioned":[162],"training.":[163],"Through":[164],"training,":[166],"learns":[169],"adjust":[171],"total":[173],"conditional":[194,200],"inputs.":[195],"Subsequently,":[196],"explore":[198],"inputs":[201],"achieve":[203],"optimal":[205],"results":[206],"each":[208],"This":[212],"training":[213],"strategy":[214],"enables":[215],"us":[216],"effectively":[218],"generation":[221],"capability":[222],"across":[225],"different":[226],"rates.":[228],"method,":[230],"named":[231],"Dual":[232],"Conditioned":[233],"VQGAN-based":[234],"Image":[235],"Compression":[236],"(DC-VIC),":[237],"outperforms":[238],"state-of-the-art":[239],"rate-distortion-perception":[244],"Code":[246],"will":[247],"be":[248],"available":[249],"at":[250],"<uri":[251],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/iwa-shi/DC_VIC</uri>":[253]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}