# Physics-Guided Variational Causal Intervention Network for Few-Shot Radar Jamming Recognition

## TL;DR

This paper introduces a new method for accurately recognizing radar jamming with few training samples by combining physics and causal inference.

## Contribution

The novel approach integrates physics-guided causal modeling with variational inference for few-shot radar jamming recognition.

## Key findings

- The proposed method outperforms existing few-shot learning baselines in low-sample scenarios.
- Incorporating physical priors improves robustness against environmental confounders.
- Causal intervention in the latent space enhances recognition accuracy.

## Abstract

Rapid and accurate recognition of radar active jamming is a prerequisite for cognitive electronic countermeasures. However, under complex electromagnetic environments with scarce training samples, existing deep learning models are prone to capturing spurious correlations induced by environmental confounders, resulting in notable performance degradation. To address this causal confounding issue, we propose a physics-guided variational causal intervention network (PG-VCIN). First, we reconstruct a structured causal model of jamming signal generation, decoupling observations into robust physical statistical features and sensitive time–frequency image representations. Physical priors are then leveraged to perform dynamic precision-weighted modulation of visual feature extraction, enforcing physical consistency at the representation learning stage. Second, we formulate deconfounding within an active inference framework and introduce a variational information bottleneck to optimize mutual information, thereby filtering out high-complexity redundant information attributable to confounders while preserving the essential causal semantics. Finally, we numerically approximate the causal effect by imposing dual intervention constraints in the latent space, including intra-class invariance and confounder invariance. Experiments on a semi-physical simulation dataset demonstrate that the proposed method achieves substantially higher recognition accuracy than several representative few-shot baselines in extremely low-sample regimes, validating the effectiveness of integrating physical mechanisms with causal inference.