{"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/ampa-net-optimization-inspired-attention","title":"AMPA-Net: Optimization-Inspired Attention Neural Network for Deep Compressed Sensing","arxiv_id":"2010.06907","date":"2020-10-14","proceeding":null,"authors":["Nanyu Li","Charles C. Zhou"],"abstract":"Compressed sensing (CS) is a challenging problem in image processing due to reconstructing an almost complete image from a limited measurement. To achieve fast and accurate CS reconstruction, we synthesize the advantages of two well-known methods (neural network and optimization algorithm) to propose a novel optimization inspired neural network which dubbed AMP-Net. AMP-Net realizes the fusion of the Approximate Message Passing (AMP) algorithm and neural network. All of its parameters are learned automatically. Furthermore, we propose an AMPA-Net which uses three attention networks to improve the representation ability of AMP-Net. Finally, We demonstrate the effectiveness of AMP-Net and AMPA-Net on four standard CS reconstruction benchmark data sets. Our code is available on https://github.com/puallee/AMPA-Net.","url_abs":"https://arxiv.org/abs/2010.06907v6","url_pdf":"https://arxiv.org/pdf/2010.06907v6.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":"ampa-net-optimization-inspired-attention","repo_url":"https://github.com/puallee/AMPA-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"compressive-sensing","task_name":"Compressive Sensing"},{"task_slug":"compressed-sensing","task_name":"compressed sensing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/compressive-sensing-on-bsd68-cs-50","task":"Compressive Sensing","dataset":"BSD68 CS=50%","model":"AMPA-Net","rank_in_archive_order":1,"of":1,"metrics":{"Average PSNR":"36.33"},"uses_additional_data":false},{"leaderboard":"/sota/compressive-sensing-on-bsds100-2x-upscaling","task":"Compressive Sensing","dataset":"BSDS100 - 2x upscaling","model":"AMPA-Net","rank_in_archive_order":1,"of":1,"metrics":{"Average PSNR":"35.95"},"uses_additional_data":false},{"leaderboard":"/sota/compressive-sensing-on-set11-cs-50","task":"Compressive Sensing","dataset":"Set11 cs=50%","model":"AMPA-Net","rank_in_archive_order":2,"of":2,"metrics":{"Average PSNR":"40.32"},"uses_additional_data":false},{"leaderboard":"/sota/compressive-sensing-on-urban100-2x-upscaling","task":"Compressive Sensing","dataset":"Urban100 - 2x upscaling","model":"AMPA-Net","rank_in_archive_order":1,"of":1,"metrics":{"Average PSNR":"35.86"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}