Out of distribution (OOD) detection has shown immense promise to enable Automatic Target Recognition models for defense applications. However, many defense applications have constraints that make current best practices for training OOD detection models challenging. These include: the need to perform fine-grained classification of identified targets, low amounts of labeled data to train models, limited availability of Subject Matter Experts to accurately label new data, and the potential need to incorporate new classes of targets as they are discovered. Given these constraints, we propose to build a fine-grained classifier with robustness against OOD data through an active learning approach - designed to further classify objects after detection through some coarse-grained object detection model. This paper will explore active learning methods for Automatic Target Recognition applications, with experiments conducted using the fine-grained overhead imagery dataset, ShipsRSImageNet, along with samples from the DOTA dataset as an exposure set. Our contributions will include recommendations to achieve fine-grained Automatic Target Recognition with robustness against OOD data with minimal labeling from Subject Matter Experts.
In most image classification applications, the task is assumed to be ”closed-set” in which the only classifications the model expects to make are of examples that it was originally trained on. However, the real world presents a much more complex ”open-set” in which a given model may encounter examples it was not trained to classify. Open-Set Recognition is the practice of enabling classifiers to recognize when they have encountered a given example that they were not previously trained to classify. Typically, these Open-Set Recognition techniques can be grouped into two categories: those that require a feature space, and those that learn a feature space. However, finding a suitable feature space is difficult and so it is often necessary that one is learned. To accomplish this, one can leverage ”Out of Distribution” examples, or examples that exist outside of the training data. This effort explores the various methods of obtaining Out of Distribution examples and how they compare. Additionally, based on our findings, we make practical recommendations for obtaining Out of Distribution examples to enable Open-Set Recognition techniques for overhead imagery and Synthetic Aperture Radar (SAR) applications.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.