Semantics- and Physics-Guided Generative Network for Radar HRRP Generalized Zero-Shot Recognition
Remote Sensing · 19.12.2025 · 18 (1) · 4
DOI: 10.3390/rs18010004 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 19.12.2025. Verfasst von Jiaqi Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, United Fund of National Key Laboratory of Automatic Target Recognition, Shanghai Municipal Commission of Economy and Informatization.
Abstract (Originalsprache)
High-resolution range profile (HRRP) target recognition has garnered significant attention in radar automatic target recognition (RATR) research for its rich structural information and low computational costs. With the rapid advancements in deep learning, methods for HRRP target recognition that leverage deep neural networks have emerged as the dominant approaches. Nevertheless, these traditional closed-set recognition methods require labeled data for every class in training, while in reality, seen classes and unseen classes coexist. Therefore, it is necessary to explore methods that can identify both seen and unseen classes simultaneously. To this end, a semantic- and physical-guided generative network (SPGGN) was innovatively proposed for HRRP generalized zero-shot recognition; it combines a constructed knowledge graph with attribute vectors to comprehensively represent semantics and reconstructs strong scattering points to introduce physical constraints. Specifically, to boost the robustness, we reconstructed the strong scattering points from deep features of HRRPs, where class-aware contrastive learning in the middle layer effectively mitigates the influence of target-aspect variations. In the classification stage, discriminative features are produced through attention-based feature fusion to capture multi-faceted information, while the design of balancing loss abates the bias towards seen classes. Experiments on two measured aircraft HRRP datasets validated the superior recognition performance of our method.
Förderung
- National Natural Science Foundation of China
- United Fund of National Key Laboratory of Automatic Target Recognition
- Shanghai Municipal Commission of Economy and Informatization
Zitieren
APA
Zhou, J., Zhang, T., Mu, S., Gao, Y., Wei, F., & Yu, W. (2025). Semantics- and Physics-Guided Generative Network for Radar HRRP Generalized Zero-Shot Recognition. Remote Sensing, 18(1), 4. https://doi.org/10.3390/rs18010004
Vancouver
Zhou J, Zhang T, Mu S, Gao Y, Wei F, Yu W. Semantics- and Physics-Guided Generative Network for Radar HRRP Generalized Zero-Shot Recognition. Remote Sensing. 2025;18(1):4. doi:10.3390/rs18010004
BibTeX
@article{Zhou2025,
author = {Zhou, Jiaqi and Zhang, Tao and Mu, Siyuan and Gao, Yuze and Wei, Feiming and Yu, Wenxian},
title = {Semantics- and Physics-Guided Generative Network for Radar HRRP Generalized Zero-Shot Recognition},
journal = {Remote Sensing},
year = {2025},
volume = {18},
number = {1},
pages = {4},
doi = {10.3390/rs18010004}
}
EUVIMED