RA-NET: AN EFFECTIVE RADAR JAMMING RECOGNITION METHOD

With the emergence of novel and complex jamming types, jamming recognition as the primary step in radar anti-jamming is facing tremendous challenges. However, traditional methods experience significant difficulties in identifying increasingly complicated jamming types due to excessive manual dependence and inferior generalization performance. To alleviate the above challenges, we propose a novel recognition framework called Residual Attention Network (RA-Net). Specifically, we integrate channel and spatial attention to learn refined feature representations, which benefits the final recognition accuracy. To further optimize our proposed method, we introduce a polynomial loss to learn a robust feature space. Experimental results on simulated datasets with 19 types of jamming have demonstrated improvement of our proposed RA-Net over traditional methods.