Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) is the key technique for remote sensing image recognition. The state-of-the-art works exploit the deep convolutional neural networks (CNNs) for SAR ATR, leading to high computation costs. These deep CNN models are unsuitable to be deployed on resource-limited platforms. In this work, we propose a graph neural network (GNN) model to achieve accurate and low-latency SAR ATR. We transform the input SAR image into the graph representation. The proposed GNN model consists of a stack of GNN layers that operates on the input graph to perform target classification. Unlike the state-of-the-art CNNs, which need heavy convolution operations, the proposed GNN model has low computation complexity and achieves comparable high accuracy. The GNN-based approach enables our proposed \emph{input pruning} strategy. By filtering out the irrelevant vertices in the input graph, we can reduce the computation complexity. Moreover, we propose the \emph{model pruning} strategy to sparsify the model weight matrices which further reduces the computation complexity. We evaluate the proposed GNN model on the MSTAR dataset and ship discrimination dataset. The evaluation results show that the proposed GNN model achieves 99.38\% and 99.7\% classification accuracy on the above two datasets, respectively. The proposed pruning strategies can prune 98.6\% input vertices and 97\% weight entries with negligible accuracy loss. Compared with the state-of-the-art CNNs, the proposed GNN model has only 1/3000 computation cost and 1/80 model size.

翻译：合成孔径雷达（SAR）自动目标识别（ATR）是遥感图像识别的关键技术。现有先进方法采用深度卷积神经网络（CNN）进行SAR ATR，导致计算成本高昂。这些深度CNN模型不适合部署在资源受限平台上。本文提出一种图神经网络（GNN）模型，以实现精确低延迟的SAR ATR。我们将输入SAR图像转换为图表示。所提出的GNN模型由堆叠的GNN层组成，作用于输入图以执行目标分类。与需要大量卷积运算的先进CNN不同，所提GNN模型计算复杂度低，且能达到相当的高精度。基于GNN的方法支持我们提出的\textit{输入剪枝}策略。通过滤除输入图中的无关顶点，可降低计算复杂度。此外，我们提出\textit{模型剪枝}策略以稀疏化模型权重矩阵，进一步降低计算复杂度。我们在MSTAR数据集和舰船判别数据集上评估了所提GNN模型。评估结果表明，所提GNN模型在上述两个数据集上的分类准确率分别达到99.38%和99.7%。所提剪枝策略可在准确率损失可忽略的前提下，剪除98.6%的输入顶点和97%的权重项。与先进CNN相比，所提GNN模型仅需1/3000的计算开销和1/80的模型尺寸。