Underwater acoustic target recognition is critical for maritime applications, yet it faces challenges arising from the complex and diverse nature of ship-radiated noise. To address these issues, we propose a robust deep learning-based framework. First, we introduce a feature extraction and fusion method based on variational mode decomposition (VMD) and the 3/2-D spectrum to generate high-fidelity 2-D DEMON spectral features, which effectively capture modulation envelope information. To further enhance feature representation, we design a one-dimensional convolutional neural network (1-D CNN) integrated with a novel Multi-Stage Multi-Type Attention Mechanism (MMATT) that adaptively refines features at different network depths. Within this mechanism, we propose a Residual Channel-Independent Spectral Attention Mechanism (R-CISAM) and a Multi-Scale Separate-and-Fuse Spectral Attention Mechanism (MS-SFSAM). Moreover, to mitigate performance degradation caused by severe class imbalance inherent in real-world ship-radiated noise data, we devise an Adjustable Class-Balanced Focal Loss (ACBFL), which provides flexibility across tasks with varying degrees of imbalance. Experimental results on a real-world ship-radiated noise dataset demonstrate that the proposed solutions effectively enhance underwater acoustic target recognition performance.

翻译：水下目标识别对海洋应用至关重要，但船舶辐射噪声的复杂多样特性使其面临挑战。针对这些问题，我们提出一种稳健的深度学习框架。首先，引入基于变分模态分解（VMD）和3/2维谱的特征提取与融合方法，生成高保真二维DEMON谱特征，有效捕获调制包络信息。为进一步增强特征表示，设计了一种集成新型多阶段多类型注意力机制（MMATT）的一维卷积神经网络（1-D CNN），可在不同网络深度自适应优化特征。在该机制中，我们提出了残差通道独立光谱注意力机制（R-CISAM）和多尺度分离融合光谱注意力机制（MS-SFSAM）。此外，为缓解实际船舶辐射噪声数据中严重的类别不平衡导致的性能下降，设计了可调节类别平衡焦点损失（ACBFL），可在不同不平衡程度的任务中提供灵活性。真实船舶辐射噪声数据集上的实验结果表明，所提方案有效提升了水下目标识别性能。