ECAPL: Open Set Recognition on HRRP Through Expansive Consistency-Aware Prototypes

The actual application of Radar Automatic Target Recognition (RATR) based on High Resolution Range Profile (HRRP) in open set environment is of significant practical importance. Implementing RATR in open set environment requires the system to correctly classify known classes of targets while ensuring known and unknown classes are distinguishable in the feature space. Additionally, the score function must be constructed for the system's decision module to reject unknown classes. To address these challenges, we propose a Expansive Consistency-Aware Prototype Learning (ECAPL) framework for Open Set Recognition (OSR). First, we propose Expansive Guidance Point Learning (EGPL), which strategically employs guidance prototype points with elastic binding constraints to enforce separation between known and unknown classes. By combining guidance points with an ideal prototype margin constraint, EGPL produces a compact abating score function for the decision module. Second, a Twin-Entanglement Framework (TEF) is proposed to leverage inconsistent unknown-class feature distributions across multiple experiments. Through dual-space correlation analysis, TEF enhances the discriminative power of prototype representations. Experimental results on measured HRRP datasets demonstrate the effectiveness and robustness of the proposed approach.