HRRP Open-Set Recognition Via Physics-Guided Pseudo-OOD Generation and Prior Decoupling

High-resolution range profile (HRRP) open-set recognition (OSR) consists of in-distribution (ID) classification and out-of-distribution (OOD) rejection. While ID classification is straightforward, overconfidence in recognition leads to failed OOD rejection because of the absence of OOD samples and constrained recognition performance during training. Overconfidence can be mitigated by generating pseudo-OOD samples and integrating prior knowledge as additional information to support OSR. However, appropriate pseudo-OOD samples should differ from ID classes while remaining within the HRRP domain. Integrating prior knowledge may cause confusion between ID and near-OOD samples with similar priors. To address this, a physics-guided HRRP OSR framework (PGR) is proposed in this article, consisting of three modules: 1) physics-guided pseudo-OOD generation (PO); 2) prior-decoupled feature extraction (PF); and 3) OOD feature loss (OFL). PO generates appropriate pseudo-OOD HRRPs based on the relationship between radial and physical scales. PF integrates prior knowledge while decoupling similar priors from OOD rejection by assigning virtual priors. OFL robustly separates pseudo-OOD and ID features using a contrastive loss. Experiments on measured and simulated HRRP datasets validate the superiority of PGR over state-of-the-art methods in far-OOD and near-OOD scenarios.