Lightweight Dual-Stream SAR-ATR Framework Based on an Attention Mechanism-Guided Heterogeneous Graph Network

Current methods synthetic aperture radar-automatic target recognition (SAR-ATR) research methods still struggle with overfitting due to small amounts of training data, as well as black-box opacity and high computational requirements. Unmanned aerial vehicles, as the mainstream means of acquiring SAR data, place higher requirements on ATR algorithms due to their flexible maneuvering characteristics. This article starts by studying the electromagnetic (EM) backscattering mechanism and the physical properties of SAR. We construct a heterogeneous graph for the first time to fully exploit both the EM scattering information of the target components and their interactions. Moreover, the multilevel multihead attention mechanism is introduced to the graph net to learn features from various topological structure levels. Additionally, we include a convolutional neural network based feature extraction net to replenish intuitive visual features. The above two nets form the lightweight dual-stream framework (LDSF). LDSF uses a feature fusion subnetwork to adaptively fuse the dual-stream features to maximize the final classification performance. The experiments use two more rigorous evaluation protocols on MSTAR and OpenSARShip, namely, once-for-all and less-for-more, which can rigorously assess the efficacy and generalization capability of the algorithms. The superiority of LDSF is verified.