CoRe-Net: Co-Operational Regressor Network with Progressive Transfer Learning for blind radar signal restoration

Real-world radar signals are frequently corrupted by various artifacts, including sensor noise, echoes, interference, and intentional jamming, differing in type, severity, and duration. Traditional radar signal restoration methods often address a single restoration problem, such as a specific noise type, and typically assume a fixed signal-to-noise ratio (SNR) level. This severely limits their usability to practical real-world applications. Several Deep Learning models have been proposed for restoration, and recently Operational Generative Adversarial Network (OpGAN) have achieved state-of-the-art performance levels. However, adversarial-based methods may still face instability and challenges with limited restoration quality refinement. This pilot study introduces a novel model, called Co-Operational Regressor Network (CoRe-Net) for blind radar signal restoration, designed to address such limitations and drawbacks. CoRe-Net replaces adversarial training with a novel cooperative learning strategy, leveraging the complementary roles of its Apprentice Regressor (AR) and Master Regressor (MR). The AR restores radar signals corrupted by various artifacts, while the MR evaluates the quality of the restoration and provides immediate and task-specific feedback, ensuring stable and efficient learning. The AR, therefore, has the advantage of both self-learning and assistive learning by the MR. The proposed model has been extensively evaluated over the benchmark Blind Radar Signal Restoration (BRSR) dataset, which simulates diverse real-world artifact scenarios. Under the fair experimental setup, this study shows that the CoRe-Net surpasses the OpGAN by more than 1 dB in mean SNR. To further boost the performance gain, this study proposes multi-pass restoration by cascaded CoRe-Nets trained with a novel paradigm called Progressive Transfer Learning (PTL), which enables iterative refinement and provides additional SNR enhancement through successive restoration passes. As a result, CoRe-Net sets a new benchmark for blind radar signal restoration by achieving state-of-the-art performance with a significant gap over a wide range of SNR levels of the input signals corrupted by various artifact types.