完整後設資料紀錄
DC 欄位語言
dc.contributor.authorWang, Chang-Jenen_US
dc.contributor.authorWen, Chao-Kaien_US
dc.contributor.authorTsai, Shang-Hoen_US
dc.contributor.authorJin, Shien_US
dc.date.accessioned2020-10-05T01:59:50Z-
dc.date.available2020-10-05T01:59:50Z-
dc.date.issued2020-01-01en_US
dc.identifier.issn1070-9908en_US
dc.identifier.urihttp://dx.doi.org/10.1109/LSP.2020.2990767en_US
dc.identifier.urihttp://hdl.handle.net/11536/154966-
dc.description.abstractPhase retrieval algorithms are now an important component of many modern computational imaging systems. A recently proposed scheme called generalized expectation consistent signal recovery (GEC-SR) shows better accuracy, speed, and robustness than numerous existing methods. Decentralized GEC-SR (deGEC-SR) addresses the scalability issue in high-resolution images. However, the convergence speed and stability of these algorithms heavily rely on the settings of several handcrafted tuning factors with inefficient turning process. In this work, we propose deGEC-SR-Net by unfolding the iterative deGEC-SR algorithm into a learning network architecture with trainable parameters. The parameters of deGEC-SR-Net are determined by data-driven training. Numerical results show that deGEC-SR-Net provides substantially faster convergence than deGEC-SR and exhibits superior robustness to noise and prior mis-specifications.en_US
dc.language.isoen_USen_US
dc.subjectPhase retrievalen_US
dc.subjectdeep neural networken_US
dc.subjectunfoldingen_US
dc.subjectdecentralized algorithmen_US
dc.titlePhase Retrieval With Learning Unfolded Expectation Consistent Signal Recovery Algorithmen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/LSP.2020.2990767en_US
dc.identifier.journalIEEE SIGNAL PROCESSING LETTERSen_US
dc.citation.volume27en_US
dc.citation.spage780en_US
dc.citation.epage784en_US
dc.contributor.department電子工程學系及電子研究所zh_TW
dc.contributor.department電控工程研究所zh_TW
dc.contributor.departmentDepartment of Electronics Engineering and Institute of Electronicsen_US
dc.contributor.departmentInstitute of Electrical and Control Engineeringen_US
dc.identifier.wosnumberWOS:000542923200001en_US
dc.citation.woscount0en_US
顯示於類別:期刊論文