SAR Target Image Classification Based on Transfer Learning and Model Compression

When convolutional neural networks (CNNs) are applied to the synthetic aperture radar (SAR) image classification, they are prone to overfitting due to scarce SAR image data, and CNNs require a large amount of storage and long computing time, so it is difficult to deploy them on resource constrained devices. This letter proposes a simple and feasible approach that can effectively solve these problems. First, the convolutional layers of the pretrained model on the Image Net data set are transferred, and a new convolutional layer and global pooling layer are added afterward. Then, fine-tuning is performed on the new network from the SAR image data set. Finally, a filter based pruning method is used on the convolutional layers to obtain a compact network. Compared with the all-convolutional network (A-ConvNets) which is the state-of-the-art method on the moving and stationary target acquisition and recognition data set, our method achieves about 3.6 x speedup during forward propagation and 3.7 x compression of the parameters, with only a 1.42% decrease in the accuracy.