Surrounding Prototype Loss for Radar HRRP Open Set Target Recognition

The open set recognition (OSR) model can identify the known and unknown samples simultaneously. In the radar automatic target recognition (RATR) application, OSR meets better practical requirements than closed set recognition (CSR). Theoretically, an overlap usually exists between the known and unknown features, which makes it difficult for the model to identify unknown samples. Therefore, we explore the distribution of the known and unknown features, and find that the unknown features are usually smaller and closer to the center region in the feature space than the known features. Based on this phenomenon, we propose a novel loss function that improves the OSR performance by controlling the known features distributed to the surrounding area of the feature space. In addition, extensive experiments are carried out on measured high-resolution range profile (HRRP) data. Thus, we verify the effectiveness of the proposed method.