{"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-learning-sparse-ternary-projections-for","title":"Deep Learning Sparse Ternary Projections for Compressed Sensing of Images","arxiv_id":"1708.08311","date":"2017-08-28","proceeding":null,"authors":["Duc Minh Nguyen","Evaggelia Tsiligianni","Nikos Deligiannis"],"abstract":"Compressed sensing (CS) is a sampling theory that allows reconstruction of\nsparse (or compressible) signals from an incomplete number of measurements,\nusing of a sensing mechanism implemented by an appropriate projection matrix.\nThe CS theory is based on random Gaussian projection matrices, which satisfy\nrecovery guarantees with high probability; however, sparse ternary {0, -1, +1}\nprojections are more suitable for hardware implementation. In this paper, we\npresent a deep learning approach to obtain very sparse ternary projections for\ncompressed sensing. Our deep learning architecture jointly learns a pair of a\nprojection matrix and a reconstruction operator in an end-to-end fashion. The\nexperimental results on real images demonstrate the effectiveness of the\nproposed approach compared to state-of-the-art methods, with significant\nadvantage in terms of complexity.","url_abs":"http://arxiv.org/abs/1708.08311v1","url_pdf":"http://arxiv.org/pdf/1708.08311v1.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-learning-sparse-ternary-projections-for","repo_url":"https://github.com/nmduc/deep-ternary","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"compressed-sensing","task_name":"compressed sensing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}