A Robust Deep Unfolded Network for Sparse Signal Recovery from Noisy Binary Measurements
This work addresses the 1-bit compressed sensing problem, which is incremental as it improves upon existing deep unfolded methods by enhancing robustness to noise.
The authors tackled the problem of sparse signal recovery from noisy binary measurements by proposing DeepFPC-ℓ₂, a deep unfolded network based on the FPC-ℓ₂ algorithm, which achieved higher reconstruction accuracy and convergence speed than the traditional method and better noise immunity than a previous deep unfolded network.
We propose a novel deep neural network, coined DeepFPC-$\ell_2$, 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 $\ell_2$-norm (FPC-$\ell_2$). The DeepFPC-$\ell_2$ method shows higher signal reconstruction accuracy and convergence speed than the traditional FPC-$\ell_2$ algorithm. Furthermore, we compare its robustness to noise with the previously proposed DeepFPC network---which stemmed from unfolding the FPC-$\ell_1$ 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.