The underwater acoustic target signal is affected by factors such as the underwater environment and the ship’s working conditions, causing the generalization of the recognition model is essential. This study is devoted to improving the generalization of recognition models, proposing a feature extraction module based on neural network and time-frequency analysis, and validating the feasibility of the model-based transfer learning method. A network-based filter based on one-dimensional convolution is built according to the calculation mode of the finite impulse response filter. An attention-based model is constructed using the convolution network components and full-connection components. The attention-based network utilizes convolution components to perform the Fourier transform and feeds back the optimization gradient of a specific task to the network-based filter. The network-based filter is designed to filter the observed signal for adaptive perception, and the attention-based model is constructed to extract the time-frequency features of the signal. In addition, model-based transfer learning is utilized to further improve the model’s performance. Experiments show that the model can perceive the frequency domain features of underwater acoustic targets, and the proposed method demonstrates competitive performance in various classification tasks on real data, especially those requiring high generalizability.

Target classification and recognition have always been complex problems in underwater acoustic signal processing because of noise interference and feature instability. In this paper, a robust feature extraction method based on multi-task learning is proposed, which provides an effective solution. Firstly, an MLP-based network model suitable for underwater acoustic signal processing is proposed to optimize feature extraction. Then, multi-task learning is deployed on the model in hard parameter-sharing so that the model can extract anti-noise interference features and embed prior feature extraction knowledge. In the model training stage, the simultaneous training method enables the model to improve the robustness and representation of classification features with the knowledge of different tasks. Furthermore, the optimized classification features are sent to the classification network to complete target recognition. The proposed method is evaluated by the dataset collected in the real environment. The results show that the proposed method effectively improves recognition accuracy and maintains high performance under different noise levels, which is better than popular methods.

Underwater acoustic target recognition (UATR) faces challenges from complex, non-stationary ship-radiated noise, which comprises a mixture of broadband, narrowband, and transient components requiring multi-scale analysis. To address this, we propose an end-to-end framework named adaptive wavelet transform with multi-task learning for underwater acoustic target recognition (AWTM-UATR). This end-to-end framework integrates an adaptive wavelet feature extraction (AWFE) front-end with learnable parameters and a joint recognition-reconstruction network (JRRN) employing multi-task learning (MTL). Additionally, it incorporates an attention-gated interaction module (AGIM) for synergistic feature fusion. The AWFE provides adaptive time-frequency analysis tailored to signal characteristics within this framework. The JRRN then learns robust features, leveraging the reconstruction task as a regularizer for the primary classification task. The AGIM further enhances classification by enabling attention-gated information flow from the reconstruction pathway. Meanwhile, the channel attention module and sparse regularization constraint (CAM & SRC) refine the features entering the JRRN. Experiments on the ShipsEar and DeepShip datasets show that AWTM-UATR achieves highly competitive performance. Furthermore, ablation studies and visualization analyses confirm the effectiveness of the key components and demonstrate the framework’s capability for robust UATR.