Physics-Guided Variational Causal Intervention Network for Few-Shot Radar Jamming Recognition
Sensors · 18.03.2026 · 26 (6) · 1900
DOI: 10.3390/s26061900 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 18.03.2026. Verfasst von Dong Xia und 8 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of China Academy of Engineering Physics, Institute of Electronic Engineering, Mianyang 621900, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CAEP Foundation.
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate School of China Academy of Engineering Physics, Institute of Electronic Engineering, Mianyang 621900, China.
- The Institute of Electronic Engineering, China Academy of Engineering Physics, Mianyang 621900, China.
Förderung
- CAEP Foundation
Zitieren
APA
Xia, D., Lv, L., Zhang, Y., Lu, Y., Li, F., Liu, L., Liu, X., Zeng, Y., & Ge, Z. (2026). Physics-Guided Variational Causal Intervention Network for Few-Shot Radar Jamming Recognition. Sensors, 26(6), 1900. https://doi.org/10.3390/s26061900
Vancouver
Xia D, Lv L, Zhang Y, Lu Y, Li F, Liu L, et al. Physics-Guided Variational Causal Intervention Network for Few-Shot Radar Jamming Recognition. Sensors. 2026;26(6):1900. doi:10.3390/s26061900
BibTeX
@article{Xia2026,
author = {Xia, Dong and Lv, Liming and Zhang, Youjian and Lu, Yanxi and Li, Fang and Liu, Lin and Liu, Xiang and Zeng, Yajun and Ge, Zhan},
title = {Physics-Guided Variational Causal Intervention Network for Few-Shot Radar Jamming Recognition},
journal = {Sensors},
year = {2026},
volume = {26},
number = {6},
pages = {1900},
doi = {10.3390/s26061900}
}
EUVIMED