Diff-SwinT: An Integrated Framework of Diffusion Model and Swin Transformer for Radar Jamming Recognition

Abstract

With the increasing complexity of radar jamming threats, accurate and automatic jamming recognition is essential but remains challenging. Conventional algorithms often suffer from sharply decreased recognition accuracy under low jamming-to-noise ratios (JNR).Artificial intelligence-based jamming signal recognition is currently the main research directions for this issue. This paper proposes a new radar jamming recognition framework called Diff-SwinT. Firstly, the time-frequency representations of jamming signals are generated using Choi-Williams distribution. Then, a diffusion model with U-Net backbone is trained by adding Gaussian noise in the forward process and reconstructing in the reverse process, obtaining an inverse diffusion model with denoising capability. Next, Swin Transformer extracts hierarchical multi-scale features from the denoised time-frequency plots, and the features are fed into linear layers for classification. Experiments show that compared to using Swin Transformer, the proposed framework improves overall accuracy by 15% to 10% at JNR from −16 dB to −8 dB, demonstrating the efficacy of diffusion-based denoising in enhancing model robustness. Compared to VGG-based and feature-fusion-based recognition methods, the proposed framework has over 27% overall accuracy advantage under JNR from −16 dB to −8 dB. This integrated approach significantly enhances intelligent radar jamming recognition capability in complex environments.

Keywords

• radar jamming recognition
• vision transformer
• diffusion model
• time-frequency analysis