MdpCaps-Csl for SAR Image Target Recognition With Limited Labeled Training Data

Abstract

Although convolutional neural networks (CNN) have shown excellent performance in many image recognition tasks, it commonly requires a lot of labeled data, and the recognition effect is frequently unsatisfied due to the limited labeled training data. In recent years, capsule network (CapsNet) has been shown to achieve a high recognition accuracy with a small group of training samples. In this study, a class separable loss based on cosine similarity is suggested to enhance the distinguishability of the extracted network. It is added as a regularization term to the original loss function to train the network, narrowing the intra-class difference and increasing the inter-class difference in each iteration. Meanwhile, a multidimensional parallel capsule module is established to obtain robust features and spatial relationships from the original images. Feature maps from convolution of different levels are extracted as the input of this module. Structural features derived from low-level convolution and semantic features derived from highlevel convolution are used for low-dimensional capsule coding and high-dimensional capsule coding, respectively. In our experiment, the general moving and stationary target acquisition and recognition (MSTAR) database is used. We find that the accuracy of the multi-dimensional parallel capsule network with class separable loss (MdpCaps-Csl) is 99.79% using all training samples, which is higher than most current recognition methods. More importantly, the accuracy is up to 97.73% even if only 10% training samples are applied, indicating MdpCaps-Csl can make excellent performance upon limited training samples. INDEX TERMS capsule network, class separable loss, image target recognition, limited labeled training data, multi-dimensional parallel capsule module, synthetic aperture radar.