{"id":"https://openalex.org/W4316660083","doi":"https://doi.org/10.1109/vcip56404.2022.10008823","title":"Improving Latent Quantization of Learned Image Compression with Gradient Scaling","display_name":"Improving Latent Quantization of Learned Image Compression with Gradient Scaling","publication_year":2022,"publication_date":"2022-12-13","ids":{"openalex":"https://openalex.org/W4316660083","doi":"https://doi.org/10.1109/vcip56404.2022.10008823"},"language":"en","primary_location":{"id":"doi:10.1109/vcip56404.2022.10008823","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip56404.2022.10008823","pdf_url":null,"source":{"id":"https://openalex.org/S4363608486","display_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-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":"https://openalex.org/A5089205282","display_name":"Heming Sun","orcid":"https://orcid.org/0000-0001-5583-4895"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]},{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]},{"id":"https://openalex.org/I4210141176","display_name":"Communication University of Zhejiang","ror":"https://ror.org/04t7gxr16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210141176"]}],"countries":["CN","JP"],"is_corresponding":true,"raw_author_name":"Heming Sun","raw_affiliation_strings":["Waseda Research Institute for Science and Engineering, Waseda University,Tokyo,Japan","JST, PRESTO, Kawaguchi, Saitama, Japan","Institutc of Information and Communication Engineering, Zhejiang University, Hangzhou, China","Waseda Research Institute for Science and Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda Research Institute for Science and Engineering, Waseda University,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"JST, PRESTO, Kawaguchi, Saitama, Japan","institution_ids":["https://openalex.org/I4210086780"]},{"raw_affiliation_string":"Institutc of Information and Communication Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210141176"]},{"raw_affiliation_string":"Waseda Research Institute for Science and Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106403416","display_name":"Lu Yu","orcid":"https://orcid.org/0000-0002-0550-7754"},"institutions":[{"id":"https://openalex.org/I4210141176","display_name":"Communication University of Zhejiang","ror":"https://ror.org/04t7gxr16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210141176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Yu","raw_affiliation_strings":["Institutc of Information and Communication Engineering, Zhejiang University,Hangzhou,China","Institutc of Information and Communication Engineering, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Institutc of Information and Communication Engineering, Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I4210141176"]},{"raw_affiliation_string":"Institutc of Information and Communication Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4210141176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002294739","display_name":"Jiro Katto","orcid":"https://orcid.org/0000-0002-1671-2614"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiro Katto","raw_affiliation_strings":["Waseda Research Institute for Science and Engineering, Waseda University,Tokyo,Japan","Waseda Research Institute for Science and Engineering, Waseda University, Tokyo, Japan","Department of Computer Science and Communication Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda Research Institute for Science and Engineering, Waseda University,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda Research Institute for Science and Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Computer Science and Communication Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089205282"],"corresponding_institution_ids":["https://openalex.org/I150744194","https://openalex.org/I4210086780","https://openalex.org/I4210141176"],"apc_list":null,"apc_paid":null,"fwci":0.06,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.34607158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9998999834060669,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9998999834060669,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9997000098228455,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9994999766349792,"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/quantization","display_name":"Quantization (signal processing)","score":0.7778812646865845},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6031870245933533},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.49303576350212097},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4823745787143707},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.4567720293998718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44789278507232666},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.44761428236961365},{"id":"https://openalex.org/keywords/linde\u2013buzo\u2013gray-algorithm","display_name":"Linde\u2013Buzo\u2013Gray algorithm","score":0.4432457387447357},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.43754372000694275},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42450982332229614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4217418432235718},{"id":"https://openalex.org/keywords/entropy-encoding","display_name":"Entropy encoding","score":0.42083340883255005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3410908877849579},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1850889027118683},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15325775742530823},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.13213613629341125},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1284623146057129},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09566053748130798},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.06634929776191711}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7778812646865845},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6031870245933533},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.49303576350212097},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4823745787143707},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.4567720293998718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44789278507232666},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.44761428236961365},{"id":"https://openalex.org/C93372532","wikidata":"https://www.wikidata.org/wiki/Q6552455","display_name":"Linde\u2013Buzo\u2013Gray algorithm","level":3,"score":0.4432457387447357},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.43754372000694275},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42450982332229614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4217418432235718},{"id":"https://openalex.org/C1769480","wikidata":"https://www.wikidata.org/wiki/Q1345239","display_name":"Entropy encoding","level":3,"score":0.42083340883255005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3410908877849579},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1850889027118683},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15325775742530823},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.13213613629341125},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1284623146057129},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09566053748130798},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.06634929776191711},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip56404.2022.10008823","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip56404.2022.10008823","pdf_url":null,"source":{"id":"https://openalex.org/S4363608486","display_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2101700394","https://openalex.org/W2242818861","https://openalex.org/W2732044853","https://openalex.org/W2785562966","https://openalex.org/W2893920456","https://openalex.org/W2962676454","https://openalex.org/W2964098744","https://openalex.org/W2982853315","https://openalex.org/W3033487655","https://openalex.org/W3034469748","https://openalex.org/W3036102031","https://openalex.org/W3091266734","https://openalex.org/W3116647679","https://openalex.org/W3172592779","https://openalex.org/W3173739377","https://openalex.org/W3176946833","https://openalex.org/W3183723309","https://openalex.org/W3193858810","https://openalex.org/W3202918664","https://openalex.org/W4294567867","https://openalex.org/W6675207249","https://openalex.org/W6741057705","https://openalex.org/W6778914582","https://openalex.org/W6779775157","https://openalex.org/W6793364766","https://openalex.org/W6797015316"],"related_works":["https://openalex.org/W2096936443","https://openalex.org/W2081863301","https://openalex.org/W2365109233","https://openalex.org/W2352648934","https://openalex.org/W2391875658","https://openalex.org/W4310608238","https://openalex.org/W4220868150","https://openalex.org/W60670607","https://openalex.org/W2025608254","https://openalex.org/W1575921859"],"abstract_inverted_index":{"Learned":[0],"image":[1],"compression":[2,8],"(LIC)":[3],"has":[4],"shown":[5],"its":[6],"superior":[7],"ability.":[9],"Quantization":[10],"is":[11,72],"an":[12],"inevitable":[13],"stage":[14],"to":[15,48,91],"generate":[16],"quantized":[17,46,70],"latent":[18,47,50,71,97],"for":[19],"the":[20,25,31,43,58,64,78,87,93,99,109],"entropy":[21],"coding.":[22],"To":[23,81],"solve":[24],"non-differentiable":[26],"problem":[27],"of":[28,45,57,95],"quantization":[29,37,65,112],"in":[30,55,77,98],"training":[32],"phase,":[33],"many":[34],"differentiable":[35],"approximated":[36],"methods":[38],"have":[39],"been":[40],"proposed.":[41],"However,":[42],"derivative":[44],"non-quantized":[49,68,96],"are":[51],"set":[52],"as":[53],"one":[54],"most":[56],"previous":[59],"methods.":[60,113],"As":[61],"a":[62],"result,":[63],"error":[66],"between":[67],"and":[69],"not":[73],"taken":[74],"into":[75],"consideration":[76],"gradient":[79,88,94],"descent.":[80],"address":[82],"this":[83],"issue,":[84],"we":[85,106],"exploit":[86],"scaling":[89],"method":[90],"scale":[92],"back-propagation.":[100],"The":[101],"experimental":[102],"results":[103],"show":[104],"that":[105],"can":[107],"outperform":[108],"recent":[110],"LIC":[111]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}