Threshold-Free Open-Set Learning Network for SAR Automatic Target Recognition

Many advanced automatic target recognition (ATR) methods for synthetic aperture radar (SAR) encounter limitations, as they heavily rely on the assumption of a closed-set environment. Consequently, these methods face challenges in effectively identifying and classifying targets from novel categories. Therefore, this article puts forward an ATR method called threshold-free open-set learning network (TfOsLN) for unknown category detection and known category recognition of SAR targets in an open world. On the basis of generative adversarial network (GAN), the proposed TfOsLN abandons the threshold-based decision-making mechanism and formulates the open-set problem as a
${K}+1$
classification problem. First, to avoid model collapse of the generator, we leverage Kullback–Leibler (KL) divergence to maximize the difference between images synthesized by two random noise inputs with the same label. Then, a dynamic-aware discriminator is proposed to dynamically learn discriminative features according to the target category, thereby enhancing the discrimination between known and unknown categories. Moreover, a multitask loss is devised to optimize the proposed method, which aims to perform well on unknown categories detection and known categories recognition. Experiments on the moving and stationary target acquisition and recognition (MSTAR) and synthetic and measured paired and labeled experiment (SAMPLE) datasets illustrate that the proposed method is superior to some state of the arts for open-set SAR target recognition tasks.