Deep Learning-Based SAR Target Recognition: A Dual-Perspective Survey of Closed Set and Open Set

Owing to the all-weather, day-and-night imaging capability of Synthetic Aperture Radar (SAR), SAR automatic target recognition (ATR) has long been a central focus in academia and industry. Since 2013, deep learning has become the dominant paradigm for SAR ATR owing to its end-to-end learning capability and robust feature-extraction capacity. To the best of our knowledge, this work provides the first systematic survey of SAR target recognition from dual closed-set and open-set perspectives and identifies four major performance bottlenecks: data scarcity, algorithmic limitations, hardware constraints, and application barriers. To address the first three bottlenecks, an in-depth analysis of closed-set solutions is presented, covering data augmentation, network optimization, and lightweight architectures. For the fourth challenge, a comprehensive analysis of open-set SAR recognition methods is provided. The intrinsic relationship and distinctions between closed-set and open-set recognition are further examined. To tackle the open-set challenge, an enhanced domain-adaptive algorithm for open-set recognition is proposed. Experiments on the OpenSAR and FUSAR datasets demonstrate at least a 3% improvement in open-set accuracy (OSA) over seven recent domain-adaptation algorithms. The rejection rate of unknown targets (RRU) reaches 80.30%, demonstrating a strong ability to distinguish unknown-class targets and offering practical insights for future research. Finally, potential directions for advancing SAR ATR are outlined, providing a comprehensive reference for the continued development of deep-learning-based SAR recognition.