English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automatic Target Recognition (ATR) algorithms classify a given SyntheticAperture Radar (SAR) image into one of the known target classes using a set oftraining images available for each class. Recently, learning methods have shownto achieve state-of-the-art classification accuracy if abundant training datais available, sampled uniformly over the classes, and their poses. In thispaper, we consider the task of ATR with a limited set of training images. Wepropose a data augmentation approach to incorporate domain knowledge andimprove the generalization power of a data-intensive learning algorithm, suchas a Convolutional neural network (CNN). The proposed data augmentation methodemploys a limited persistence sparse modeling approach, capitalizing oncommonly observed characteristics of wide-angle synthetic aperture radar (SAR)imagery. Specifically, we exploit the sparsity of the scattering centers in thespatial domain and the smoothly-varying structure of the scatteringcoefficients in the azimuthal domain to solve the ill-posed problem ofover-parametrized model fitting. Using this estimated model, we synthesize newimages at poses and sub-pixel translations not available in the given data toaugment CNN's training data. The experimental results show that for thetraining data starved region, the proposed method provides a significant gainin the resulting ATR algorithm's generalization performance.

Sparse Signal Models for Data Augmentation in Deep Learning ATR