An effective convolutional and transformer cooperation network for underwater acoustic target recognition

Underwater acoustic target recognition (UATR) is a key technology in the field of underwater acoustic information processing. In recent years, models based on convolutional neural networks (CNN) have shown excellent performance in the domain of UATR. However, CNN have limitations in capturing the global information of underwater acoustic features. Due to its advantages in modeling global dependencies, the Transformer model is gradually gaining attention from researchers. In order to capture the time-frequency dependencies in acoustic spectrograms more effectively, this paper proposes a recognition model based on the Mel spectrogram that combines CNN with the Transformer, named the underwater acoustics CNN-Transformer cooperation network (UACTC). Compared to the Transformer alone, this model is more efficient in extracting local features. The CNN module uses a residual network based on the efficient channel attention (ECA) module for efficient deep feature extraction. Additionally, the ECA module is introduced into the Transformer block to enhance the channel feature extraction of the Transformer. Experiments prove that the ECA module effectively improves the performance of the recognition system. The effectiveness of the proposed model has been validated on two public datasets, achieving 98.05 % and 96.96 % on the ShipsEar and DeepShip datasets, respectively.