Sparse Signal Models for Data Augmentation in Deep Learning ATR
This work provides an incremental improvement for deep learning-based ATR systems, particularly for scenarios where training data is scarce, by improving their generalization performance.
This paper addresses the challenge of Automatic Target Recognition (ATR) with limited training data by proposing a data augmentation method. It synthesizes new Synthetic Aperture Radar (SAR) images by exploiting the sparsity of scattering centers and the smooth variation of scattering coefficients, leading to significant generalization performance gains for deep learning ATR algorithms in data-starved scenarios.
Automatic Target Recognition (ATR) algorithms classify a given Synthetic Aperture Radar (SAR) image into one of the known target classes using a set of training images available for each class. Recently, learning methods have shown to achieve state-of-the-art classification accuracy if abundant training data is available, sampled uniformly over the classes, and their poses. In this paper, we consider the task of ATR with a limited set of training images. We propose a data augmentation approach to incorporate domain knowledge and improve the generalization power of a data-intensive learning algorithm, such as a Convolutional neural network (CNN). The proposed data augmentation method employs a limited persistence sparse modeling approach, capitalizing on commonly observed characteristics of wide-angle synthetic aperture radar (SAR) imagery. Specifically, we exploit the sparsity of the scattering centers in the spatial domain and the smoothly-varying structure of the scattering coefficients in the azimuthal domain to solve the ill-posed problem of over-parametrized model fitting. Using this estimated model, we synthesize new images at poses and sub-pixel translations not available in the given data to augment CNN's training data. The experimental results show that for the training data starved region, the proposed method provides a significant gain in the resulting ATR algorithm's generalization performance.