Meta-Learner-Based Stacking Network on Space Target Recognition for ISAR Images
Yun Zhang, Haoxuan Yuan, Hongbo Li, Jiaying Chen, Muqun Niu
Abstract
Recently, the deep learning models have achieved great success in the recognition of inverse synthetic aperture radar (ISAR) images. However, most of the deep learning models fail to obtain satisfactory results under the condition of small samples due to the contradiction between the large parameter space of the deep learning models and the insufficient labeled samples of space target imaging by ISAR. In this paper, a method of meta-learner based stack- ing network (MSN) is proposed, which can realize the high- precision classification of space target by ISAR images under the condition of small sample. Innovatively, a rotation-invariant attention mechanism (RAM) module is added into Resnet50 network to magnify the difference of embedded features of target and background. Complementarily, the deep relationship between the features of fine-grained ISAR image is extracted by using graph convolutional network (GCN) and relation network (RN). Finally, an innovative adaptive weighted XGBoost algorithm is used to integrate the prediction results of the base learners. The main contributions of this paper include proposing a RAM module and using an innovative adaptive weighted XGBoost algorithm to realize ensemble learning. The experiment results show that the RAM module effectively concentrates the networks attention on the recognized target, and the recognition rate of MSN is about 5% higher than that of a single base learner under different data volume conditions, which proves that MSN achieves competitive accuracy against other state-of-the-art approaches.