Abstract: Due to the complex and changeable marine environment, the active sonar target recognition problem has always been difficult in the field of underwater acoustics. Deep learning-based fusion recognition technology provides an effective way to solve this problem, but relying on simple concatenation strategies to fuse multi-domain features can cause information redundancy, and it isn't easy to effectively mine correlation information between domains. Therefore, this paper proposes an attention mechanism-based multi-domain feature fusion recognition method for active sonar targets. In the method, by preprocessing active sonar echo signals and constructing a multi-domain feature extraction and fusion network, this network uses a 1-DCNN-LSTM series network and a 2-DCNN network with channel attention introduced respectively to extract deep features from different domains. Subsequently, combining feature concatenation and constructing multi-domain cross-attention, intra-domain and cross-domain feature fusion are performed, which can effectively eliminate redundant information and promote inter-domain information interaction while maximizing the retention of target features. Experimental results show that compared with single-domain methods, the network using an attention mechanism for multi-domain feature fusion strengthens cross-domain information interaction and significantly improves feature representation capability. Compared with other methods, the recognition method in this paper also has obvious advantages in performance and maintains stable generalization ability in scenarios with a low signal-clutter ratio.