Ultra-lightweight CNN design based on neural architecture search and knowledge distillation: A novel method to build the automatic recognition model of space target ISAR images

作者：Hong Yang, Yasheng Zhang, Can-bin Yin, Wenzhe Ding · 发表于：Defence Technology · 年份：2021 · DOI：10.1016/j.dt.2021.04.014 · 被引用次数：24 · 研究领域：Advanced SAR Imaging Techniques、Synthetic Aperture Radar (SAR) Applications and Techniques、Optical Systems and Laser Technology

In this paper, a novel method of ultra-lightweight convolution neural network (CNN) design based on neural architecture search (NAS) and knowledge distillation (KD) is proposed. It can realize the automatic construction of the space target inverse synthetic aperture radar (ISAR) image recognition model with ultra-lightweight and high accuracy. This method introduces the NAS method into the radar image recognition for the first time, which solves the time-consuming and labor-consuming problems in the artificial design of the space target ISAR image automatic recognition model (STIIARM). On this basis, the NAS model's knowledge is transferred to the student model with lower computational complexity by the flow of the solution procedure (FSP) distillation method. Thus, the decline of recognition accuracy caused by the direct compression of model structural parameters can be effectively avoided, and the ultra-lightweight STIIARM can be obtained. In the method, the Inverted Linear Bottleneck (ILB) and Inverted Residual Block (IRB) are firstly taken as each block's basic structure in CNN. And the expansion ratio, output filter size, number of IRBs, and convolution kernel size are set as the search parameters to construct a hierarchical decomposition search space. Then, the recognition accuracy and computational complexity are taken as the objective function and constraint conditions, respectively, and the global optimization model of the CNN architecture search is established. Next...