Open Set Recognition With Incremental Learning for SAR Target Classification

Synthetic aperture radar (SAR) target classification is an important application in SAR image interpretation. In practical applications, the battlefield is open and dynamic, and the SAR target classification model often encounters the targets of unknown classes. However, most of the existing SAR target classification methods follow the close-set assumption. It makes them only classify several fixed classes of targets and cannot deal with the targets from unknown classes. To this end, this article proposes a novel SAR target classification method. This method can not only classify the targets from known classes and search targets from unknown classes but also incrementally update the classification model with these unknown class targets. Specifically, an autoencoder improved by multiscale structural similarity (MS-SSIM) loss is utilized to extract targets' features, and it can better utilize the structural information in SAR images. Next, the classifier based on extreme value theorem (EVT) is established, which can classify the known class targets and search the unknown class targets. Then, we perform improved model reduction on the established classifier. This operation could speed up the model and prepare for incremental learning. Finally, after manually labeling those unknown class targets, the classifier is updated with these data in incremental form. Experimental results on the moving and stationary target automatic recognition (MSTAR) dataset indicate that, compared with the state-of-the-art methods, our proposed method has a better performance in open set recognition and incremental learning.