Abstract
The reemergence of Deep Neural Networks (DNNs) has lead to high-performance supervised learning algorithms for the Electro-Optical (EO) domain classification and detection problems. This success is because generating huge labeled datasets has become possible using modern crowdsourcing labeling platforms such as Amazon’s Mechanical Turk that recruit ordinary people to label data. Unlike the EO domain, labeling the Synthetic Aperture Radar (SAR) domain data can be much more challenging, and for various reasons, using crowdsourcing platforms is not feasible for labeling the SAR domain data. As a result, training deep networks using supervised learning is more challenging in the SAR domain. In the paper, we present a new framework to train a deep neural network for classifying Synthetic Aperture Radar (SAR) images by eliminating the need for a huge labeled dataset. Our idea is based on transferring knowledge from a related EO domain problem, where labeled data are easy to obtain. We transfer knowledge from the EO domain through learning a shared invariant cross-domain embedding space that is also discriminative for classification. To this end, we train two deep encoders that are coupled through their last year to map data points from the EO and the SAR domains to the shared embedding space such that the distance between the distributions of the two domains is minimized in the latent embedding space. We use the Sliced Wasserstein Distance (SWD) to measure and minimize the distance between these two distributions and use a limited number of SAR label data points to match the distributions class-conditionally. As a result of this training procedure, a classifier trained from the embedding space to the label space using mostly the EO data would generalize well on the SAR domain. We provide a theoretical analysis to demonstrate why our approach is effective and validate our algorithm on the problem of ship classification in the SAR domain by comparing against several other competing learning approaches.
Highlights
And prior to the emergence of machine learning, most imaging devices were designed first to generate outputs that were interpretable by humans, mostly natural images
We develop a method that benefits from cross-domain knowledge transfer from a related task in EO domains as the source domain to address a task in Synthetic Aperture Radar (SAR) domains as the target domain
We addressed the problem of SAR image classification when only a few labeled data are available
Summary
And prior to the emergence of machine learning, most imaging devices were designed first to generate outputs that were interpretable by humans, mostly natural images. The dominant visual data that are collected even currently are the Electro-Optical (EO) domain data. Digital EO images are generated by a planner grid of sensors that detect and record the magnitude and the color of reflected visible light from the surface of an object in the from of a planner array of pixels. Most machine learning algorithms that are developed for automation process EO domain data as their input. The area of EO-based machine learning and computer vision has been successful in developing classification and detection algorithms with human-level performance for many applications. Reemergence of neural networks in the form deep Convolutional
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
