{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-multiple-description-coding-by-learning","title":"Deep Multiple Description Coding by Learning Scalar Quantization","arxiv_id":"1811.01504","date":"2018-11-05","proceeding":null,"authors":["Lijun Zhao","Huihui Bai","Anhong Wang","Yao Zhao"],"abstract":"In this paper, we propose a deep multiple description coding framework, whose\nquantizers are adaptively learned via the minimization of multiple description\ncompressive loss. Firstly, our framework is built upon auto-encoder networks,\nwhich have multiple description multi-scale dilated encoder network and\nmultiple description decoder networks. Secondly, two entropy estimation\nnetworks are learned to estimate the informative amounts of the quantized\ntensors, which can further supervise the learning of multiple description\nencoder network to represent the input image delicately. Thirdly, a pair of\nscalar quantizers accompanied by two importance-indicator maps is automatically\nlearned in an end-to-end self-supervised way. Finally, multiple description\nstructural dissimilarity distance loss is imposed on multiple description\ndecoded images in pixel domain for diversified multiple description generations\nrather than on feature tensors in feature domain, in addition to multiple\ndescription reconstruction loss. Through testing on two commonly used datasets,\nit is verified that our method is beyond several state-of-the-art multiple\ndescription coding approaches in terms of coding efficiency.","url_abs":"http://arxiv.org/abs/1811.01504v3","url_pdf":"http://arxiv.org/pdf/1811.01504v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-multiple-description-coding-by-learning","repo_url":"https://github.com/mdcnn/mdcnn.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}