Abstract
The limitations of existing Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) methods lie in their confinement by the closed-environment assumption, hindering their effective and robust handling of unknown target categories in open environments. Open Set Recognition (OSR), a pivotal facet for algorithmic practicality, intends to categorize known classes while denoting unknown ones as “unknown.” The chief challenge in OSR is to mitigate risks associated with numerous unknown samples within the open space. To enhance open-set SAR classification, a method called scattering kernel with reciprocal learning network is proposed. Initially, a feature representing paradigm is constructed on the base of reciprocal point learning (RPL), establishing a bounded space for potential unknown classes. This approach indirectly introduces unknown information into a learner confined to known classes, thereby acquiring more concise and discriminative representations. Subsequently, considering the variability in the imaging of targets at different angles and the discreteness of components in SAR images, a proposal is made to design large-sized convolutional kernels based on attribute scattering center (ASC) models. This enhances the ability to extract intrinsic non-linear features and specific scattering characteristics in SAR images, thereby improving the discriminative features of the model and mitigating the impact of imaging variations on classification performance. Experiments conducted on the public datasets substantiate the superior performance of this approach called ASC-RPL over mainstream methods.