A Lightweight Time–Frequency–Space Dual-Stream Network for Active Sonar-Based Underwater Target Recognition

Accurate underwater target recognition is challenged by high noise levels, signal attenuation, multipath reflections, and the need for efficient real-time processing in complex environments. To overcome these obstacles, we propose the lightweight time–frequency–space dual-stream network (LTFSD-Net), which is a novel framework designed to enhance active sonar target recognition by effectively extracting and fusing spatial-, temporal-, and frequency-domain features. Our dual-stream architecture incorporates a beamforming-based spatial attention mechanism (SAM) and a depth attention mechanism (DAM), enabling the network to focus on critical regions of target echoes and improve feature extraction. In addition, lightweight depthwise separable convolutional modules facilitate efficient time-frequency feature extraction, ensuring computational efficiency that is suitable for real-time applications. We introduce a novel feature fusion strategy that uses tensor decomposition at the front-end and compact bilinear pooling (CBP) at the back-end. This approach seamlessly combines low- and high-level features, thereby enhancing the discriminative capabilities of the model. Extensive experiments conducted on both the sea trial and anechoic pool datasets demonstrated that LTFSD-Net achieved overall accuracies of 84.36% and 92.88%, respectively. The proposed method outperformed existing state-of-the-art (SOTA) approaches in terms of both accuracy and computational efficiency, underscoring its effectiveness and efficiency. Our findings highlight its potential for integration into advanced sensor systems for enhanced underwater acoustic target recognition (UATR).