[{"_1":2,"_3":-5,"_4":-5},"loaderData",{"_5":6,"_7":8,"_9":10},"actionData","errors","root",{"_270":271},"routes/_layout",{"_11":190},"routes/entity.$type.$id",{"_11":12,"_13":14,"_15":16,"_17":18,"_19":20,"_21":22,"_23":24,"_25":26,"_27":28},"dehydratedState",{"_73":74,"_75":76},"type","paper","id","paper_W3016715915","section","technologies","entity",{"_15":16,"_29":30,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":38,"_39":-5,"_40":41,"_42":43,"_44":45,"_46":47,"_48":-5,"_49":50,"_51":30,"_52":53,"_54":55,"_56":57,"_58":59,"_60":61,"_62":-5,"_63":64,"_65":-5,"_66":67,"_68":30,"_69":-5},"canonical","https://www.hugmap.com/entity/paper/paper_W3016715915/technologies","siteBaseUrl","https://www.hugmap.com","sectionCount",2,"jsonLd","{\"@context\":\"https://schema.org\",\"@graph\":[{\"name\":\"DeepJSCC-f: Deep Joint Source-Channel Coding of Images With Feedback\",\"url\":\"https://www.hugmap.com/entity/paper/paper_W3016715915/technologies\",\"@type\":\"ScholarlyArticle\",\"headline\":\"DeepJSCC-f: Deep Joint Source-Channel Coding of Images With Feedback\",\"datePublished\":\"2020-04-14\",\"isPartOf\":{\"@type\":\"Periodical\",\"name\":\"IEEE Journal on Selected Areas in Information Theory\"}},{\"@type\":\"CollectionPage\",\"name\":\"DeepJSCC-f: Deep Joint Source-Channel Coding of Images With Feedback 相关技术\",\"description\":\"DeepJSCC-f: Deep Joint Source-Channel Coding of Images With Feedback 在 HugMap 中的相关技术，共 2 条，含结构化关联信息与详情链接。\",\"url\":\"https://www.hugmap.com/entity/paper/paper_W3016715915/technologies\",\"inLanguage\":\"zh-CN\"},{\"@type\":\"BreadcrumbList\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"首页\",\"item\":\"https://www.hugmap.com/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"论文\",\"item\":\"https://www.hugmap.com/search?type=paper\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"DeepJSCC-f: Deep Joint Source-Channel Coding of Images With Feedback\",\"item\":\"https://www.hugmap.com/entity/paper/paper_W3016715915\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"相关技术\",\"item\":\"https://www.hugmap.com/entity/paper/paper_W3016715915/technologies\"}]}]}","name","DeepJSCC-f: Deep Joint Source-Channel Coding of Images With Feedback","nameZh","aliases","description","descriptionZh","status","active","externalIds","{\"openalex\":\"W3016715915\",\"doi\":\"10.1109/jsait.2020.2987203\"}","properties","source","openalex","createdAt","2026-05-19T17:53:51.203714556","updatedAt","2026-05-19T17:53:51.204127372","doi","10.1109/jsait.2020.2987203","arxivId","openalexId","W3016715915","title","abstractText","We consider wireless transmission of images in the presence of channel output feedback. From a Shannon theoretic perspective feedback does not improve the asymptotic end-to-end performance, and separate source coding followed by capacity-achieving channel coding, which ignores the feedback signal, achieves the optimal performance. It is well known that separation is not optimal in the practical finite blocklength regime; however, there are no known practical joint source-channel coding (JSCC) schemes that can exploit the feedback signal and surpass the performance of separation-based schemes. Inspired by the recent success of deep learning methods for JSCC, we investigate how noiseless or noisy channel output feedback can be incorporated into the transmission system to improve the reconstruction quality at the receiver. We introduce an autoencoder-based JSCC scheme, which we call DeepJSCC-f , that exploits the channel output feedback, and provides considerable improvements in terms of the end-to-end reconstruction quality for fixed-length transmission, or in terms of the average delay for variable-length transmission. To the best of our knowledge, this is the first practical JSCC scheme that can fully exploit channel output feedback, demonstrating yet another setting in which modern machine learning techniques can enable the design of new and efficient communication methods that surpass the performance of traditional structured coding-based designs.","publishedDate","2020-04-14","publishedYear",2020,"venue","IEEE Journal on Selected Areas in Information Theory","citationCount",391,"authors","keywords",[70,71,72],"pdfUrl","topVenue",false,"displayName","displayDescription","Speech and Audio Processing","Wireless Signal Modulation Classification","Sparse and Compressive Sensing Techniques","mutations",[],"queries",[77],{"_78":79,"_80":81,"_82":83,"_84":85},"dehydratedAt",1781652476302,"state",{"_87":88,"_89":90,"_91":92,"_93":-5,"_94":95,"_96":95,"_97":95,"_98":-5,"_99":-5,"_100":67,"_35":101,"_102":103},"queryKey",[86,19,14,16],"queryHash","[\"portal\",\"entity\",\"paper\",\"paper_W3016715915\"]","portal","data",{"_19":20,"_104":105,"_106":107,"_108":109,"_110":111,"_18":112,"_62":113},"dataUpdateCount",1,"dataUpdatedAt",1781652476301,"error","errorUpdateCount",0,"errorUpdatedAt","fetchFailureCount","fetchFailureReason","fetchMeta","isInvalidated","success","fetchStatus","idle","entityType","Paper","taxonomies",[157,158,159],"events",[],"articles",[],[137,138],[114,115],{"_15":131,"_29":132,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":133,"_39":-5,"_40":41,"_42":134,"_44":135,"_121":136,"_51":-5,"_123":-5,"_124":-5,"_125":-5,"_60":-5,"_126":-5,"_127":-5,"_128":-5,"_129":-5,"_130":-5,"_68":132,"_69":-5},{"_15":116,"_29":117,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":118,"_39":-5,"_40":41,"_42":119,"_44":120,"_121":122,"_51":-5,"_123":-5,"_124":-5,"_125":-5,"_60":-5,"_126":-5,"_127":-5,"_128":-5,"_129":-5,"_130":-5,"_68":117,"_69":-5},"person_A5044611289","David Burth Kurka","{\"openalex\":\"A5044611289\",\"orcid\":\"0000-0002-3754-3290\"}","2026-05-14T10:11:19.1855678","2026-05-21T13:45:48.287043343","orcid","0000-0002-3754-3290","affiliation","researchArea","paperCount","homepage","linkedin","twitter","github","hindex","person_A5016883501","Denız Gündüz","{\"openalex\":\"A5016883501\",\"orcid\":\"0000-0002-7725-395X\"}","2026-05-14T10:11:19.295080501","2026-05-23T04:19:05.25789452","0000-0002-7725-395X",{"_15":153,"_29":70,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":154,"_39":-5,"_40":141,"_42":155,"_44":156,"_144":145,"_146":147,"_148":-5,"_149":150,"_151":-5,"_125":-5,"_152":-5,"_68":70,"_69":-5},{"_15":139,"_29":71,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":140,"_39":-5,"_40":141,"_42":142,"_44":143,"_144":145,"_146":147,"_148":-5,"_149":150,"_151":-5,"_125":-5,"_152":-5,"_68":71,"_69":-5},"tech_oa_T12131","{\"taxonomy_id\":\"tax_rd_T12131\"}","openalex_topics","2026-05-17T09:00:14.369549608","2026-05-17T09:00:14.369551013","techType","concept","domain","Physical Sciences","proposedYear","maturityLevel","growing","wikipediaUrl","patentCount","tech_oa_T10860","{\"taxonomy_id\":\"tax_rd_T10860\"}","2026-05-17T09:00:26.288236047","2026-05-17T09:00:26.288237777",{"_15":184,"_29":71,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":185,"_39":-5,"_40":41,"_42":186,"_44":187,"_164":165,"_166":-5,"_167":168,"_169":188,"_171":189,"_173":95,"_174":175,"_176":95,"_177":-5,"_68":71,"_69":-5},{"_15":178,"_29":72,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":179,"_39":-5,"_40":41,"_42":180,"_44":181,"_164":165,"_166":-5,"_167":168,"_169":182,"_171":183,"_173":95,"_174":175,"_176":95,"_177":-5,"_68":72,"_69":-5},{"_15":160,"_29":70,"_31":-5,"_32":-5,"_33":-5,"_34":-5,"_35":36,"_37":161,"_39":-5,"_40":41,"_42":162,"_44":163,"_164":165,"_166":-5,"_167":168,"_169":170,"_171":172,"_173":95,"_174":175,"_176":95,"_177":-5,"_68":70,"_69":-5},"tax_rd_T10860","{\"openalex_topic\":\"T10860\"}","2026-05-14T00:41:22.198739599","2026-05-23T12:40:03.19452842","taxonomyType","RESEARCH_DOMAIN","code","level",3,"parentId","tax_rd_1711","path","Physical Sciences/Computer Science/Signal Processing/Speech and Audio Processing","sortOrder","isLeaf",true,"entityCount","children","tax_rd_T10500","{\"openalex_topic\":\"T10500\"}","2026-05-14T00:30:27.19960051","2026-05-23T12:39:17.252016307","tax_rd_2206","Physical Sciences/Engineering/Computational Mechanics/Sparse and Compressive Sensing Techniques","tax_rd_T12131","{\"openalex_topic\":\"T12131\"}","2026-05-14T00:29:52.370738847","2026-05-23T11:43:21.261923017","tax_rd_1702","Physical Sciences/Computer Science/Artificial Intelligence/Wireless Signal Modulation Classification",{"_73":191,"_75":192},[],[193],{"_78":194,"_80":195,"_82":196,"_84":197},1781652468896,{"_87":199,"_89":90,"_91":194,"_93":-5,"_94":95,"_96":95,"_97":95,"_98":-5,"_99":-5,"_100":67,"_35":101,"_102":103},[86,198],"[\"portal\",\"industries\"]","industries",[200,201,202,203,204,205,206,207,208,209,210,211],{"_15":263,"_29":264,"_31":-5,"_32":265,"_33":266,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":267,"_173":95,"_174":67,"_176":95,"_177":-5,"_68":264,"_69":266},{"_15":259,"_29":260,"_31":-5,"_32":-5,"_33":261,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":262,"_173":95,"_174":67,"_176":95,"_177":-5,"_68":260,"_69":261},{"_15":253,"_29":254,"_31":-5,"_32":255,"_33":256,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":257,"_173":95,"_174":67,"_176":95,"_177":-5,"_68":254,"_69":256},{"_15":249,"_29":250,"_31":-5,"_32":-5,"_33":251,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":252,"_173":95,"_174":67,"_176":95,"_177":-5,"_68":250,"_69":251},{"_15":245,"_29":246,"_31":-5,"_32":-5,"_33":247,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":248,"_173":95,"_174":67,"_176":95,"_177":-5,"_68":246,"_69":247},{"_15":239,"_29":240,"_31":-5,"_32":241,"_33":242,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":243,"_173":95,"_174":67,"_176":95,"_177":-5,"_68":240,"_69":242},{"_15":235,"_29":236,"_31":-5,"_32":-5,"_33":237,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":238,"_173":95,"_174":175,"_176":95,"_177":-5,"_68":236,"_69":237},{"_15":231,"_29":232,"_31":-5,"_32":-5,"_33":233,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":234,"_173":95,"_174":67,"_176":95,"_177":-5,"_68":232,"_69":233},{"_15":227,"_29":228,"_31":-5,"_32":-5,"_33":229,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":230,"_173":95,"_174":67,"_176":95,"_177":-5,"_68":228,"_69":229},{"_15":223,"_29":224,"_31":-5,"_32":-5,"_33":225,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":226,"_173":95,"_174":67,"_176":95,"_177":-5,"_68":224,"_69":225},{"_15":219,"_29":220,"_31":-5,"_32":-5,"_33":221,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":222,"_173":95,"_174":67,"_176":95,"_177":-5,"_68":220,"_69":221},{"_15":212,"_29":213,"_31":-5,"_32":-5,"_33":214,"_34":-5,"_35":36,"_37":-5,"_39":-5,"_40":215,"_42":-5,"_44":-5,"_164":216,"_166":-5,"_167":90,"_169":217,"_171":218,"_173":95,"_174":67,"_176":95,"_177":-5,"_68":213,"_69":214},"tax_ind_smartphone","智能手机","Smartphone","manual","INDUSTRY","tax_ind_root","科技行业/智能手机","tax_ind_robot","机器人","Robotics","科技行业/机器人","tax_ind_wearable","智能穿戴","Smart Wearables","科技行业/智能穿戴","tax_ind_energy","新能源与智能制造","New Energy & Smart Manufacturing","科技行业/新能源与智能制造","tax_ind_biotech","生物科技","Biotech","科技行业/生物科技","tax_ind_quantum","量子计算","Quantum Computing","科技行业/量子计算","tax_ind_blockchain","区块链",[244],"Blockchain","科技行业/区块链","Web3","tax_ind_enterprise","企业软件","Enterprise Software","科技行业/企业软件","tax_ind_security","网络安全","Cybersecurity","科技行业/网络安全","tax_ind_semi","半导体",[258],"Semiconductor","科技行业/半导体","芯片","tax_ind_cloud","云计算","Cloud Computing","科技行业/云计算","tax_ind_ai","人工智能",[268,269],"Artificial Intelligence","科技行业/人工智能","AI","AI 技术","env",{"_272":24},"SITE_BASE_URL"]

DeepJSCC-<i>f</i>: Deep Joint Source-Channel Coding of Images With Feedback 论文

DeepJSCC-<i>f</i>: Deep Joint Source-Channel Coding of Images With Feedback · 相关技术

相关技术