{"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/cae-admm-implicit-bitrate-optimization-via","title":"CAE-ADMM: Implicit Bitrate Optimization via ADMM-based Pruning in Compressive Autoencoders","arxiv_id":"1901.07196","date":"2019-01-22","proceeding":null,"authors":["Haimeng Zhao","Peiyuan Liao"],"abstract":"We introduce ADMM-pruned Compressive AutoEncoder (CAE-ADMM) that uses\nAlternative Direction Method of Multipliers (ADMM) to optimize the trade-off\nbetween distortion and efficiency of lossy image compression. Specifically,\nADMM in our method is to promote sparsity to implicitly optimize the bitrate,\ndifferent from entropy estimators used in the previous research. The\nexperiments on public datasets show that our method outperforms the original\nCAE and some traditional codecs in terms of SSIM/MS-SSIM metrics, at reasonable\ninference speed.","url_abs":"http://arxiv.org/abs/1901.07196v4","url_pdf":"http://arxiv.org/pdf/1901.07196v4.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":"cae-admm-implicit-bitrate-optimization-via","repo_url":"https://github.com/JasonZHM/CAE-ADMM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"cae-admm-implicit-bitrate-optimization-via","repo_url":"https://github.com/JasonZHM/CAEP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-compression","task_name":"Image Compression"},{"task_slug":"ms-ssim","task_name":"MS-SSIM"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"ssim","task_name":"SSIM"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}