A Robust Deep Unfolded Network for Sparse Signal Recovery from Noisy Binary Measurements
A Robust Deep Unfolded Network for Sparse Signal Recovery from Noisy Binary Measurements
复制标题
DOI：
10.23919/eusipco47968.2020.9287582
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Yuqing Yang;Peng Xiao;Bin Liao;Nikos Deligiannis
中科院分区：
文献类型：
--
作者：
Yuqing Yang;Peng Xiao;Bin Liao;Nikos Deligiannis
我们提出了一种新的深度神经网络，称为DeepFPC -2，用于解决1位压缩感知问题。该网络是通过展开具有单侧范数的定点延拓（FPC）算法（FPC-FPC 2）的迭代来设计的。DeepFPC-102方法比传统的FPC-102算法具有更高的信号重构精度和收敛速度。此外，我们将其对噪声的鲁棒性与先前提出的DeepFPC网络进行了比较-该网络源于展开FPC-FPC 1算法-用于不同的信噪比（SNR）和符号翻转比（翻转比）场景。我们表明，所提出的网络比以前的DeepFPC方法具有更好的抗噪性。这一结果表明，深度展开神经网络的鲁棒性与其所源自的算法的鲁棒性有关。
We propose a novel deep neural network, coined DeepFPC -ℓ2, for solving the 1-bit compressed sensing problem. The network is designed by unfolding the iterations of the fixed-point continuation (FPC) algorithm with one-sided ℓ2-norm (FPC-ℓ2). The DeepFPC-ℓ2 method shows higher signal reconstruction accuracy and convergence speed than the traditional FPC-ℓ2 algorithm. Furthermore, we compare its robustness to noise with the previously proposed DeepFPC network—which stemmed from unfolding the FPC-ℓ1 algorithm—for different signal to noise ratio (SNR) and sign-flipped ratio (flip ratio) scenarios. We show that the proposed network has better noise immunity than the previous DeepFPC method. This result indicates that the robustness of a deep-unfolded neural network is related with that of the algorithm it stems from.