Interference Suppression for Synthetic Aperture Radar Using Dual-Path Residual Network with Attention Mechanism

The existence of Comb Spectrum Modulation Jamming (CSMJ) degrades the imaging quality severely, which hinders the performance of Synthetic Aperture Radar (SAR). The frequency domain-notched filtering is applicable in dealing with CSMJ but would introduce severe signal loss. In this paper, we propose a novel method for CSMJ suppression based on a dual-path residual network with the attention mechanism (DPRA-Net). We use the attention mechanism to build inter-dependencies among local and global features in the frequency domain for improving the suppression performance of DPAR-Net. Consequently, the CSMJ suppression problem is transformed into an end-to-end mapping problem, which minimizes signal loss. The validity of our algorithm has been verified on the measured data collected by Sentinel-1.