Deep Neural Networks (DNNs) do not inherently compute or exhibit empirically-justified task confidence. In mission critical applications, it is important to both understand associated DNN reasoning and its supporting evidence. In this paper, we propose a novel Bayesian approach to extract explanations, justifications, and uncertainty estimates from DNNs. Our approach is efficient both in terms of memory and computation, and can be applied to any black box DNN without any retraining, including applications to anomaly detection and out-of-distribution detection tasks. We validate our approach on the CIFAR-10 dataset, and show that it can significantly improve the interpretability and reliability of DNNs.
Object representation is fundamental to Automated Target Recognition (ATR). Many ATR approaches choose a basis, such as a wavelet or Fourier basis, to represent the target. Recently, advancements in Image and Signal processing have shown that object recognition can be improved if, rather than a assuming a basis, a database of training examples is used to learn a representation. We discuss learning representations using Non-parametric Bayesian topic models, and demonstrate how to integrate information from other sources to improve ATR. We apply the method to EO and IR information integration for vehicle target identification and show that the learned representation of the joint EO and IR information improves target identification by 4%. Furthermore, we demonstrate that we can integrate text and imagery data to direct the representation for mission specific tasks and improve performance by 8%. Finally, we illustrate integrating graphical models into representation learning to improve performance by 2%.
A canonical problem for autonomy is search and discovery. Often, searching needs to be unpredictable in order
to be effective. In this paper, we investigate and compare the effectiveness of the traditional and predictable
lawnmower search strategy to that of a random search. Specifically the family of searches with paths determined
by heavy tailed distributions called Lévy stable searches is investigated. These searches are characterized by long
flight paths, followed by a new random direction, with the flight path lengths determined by the distribution
parameter α. Two basic search scenarios are considered in this study: stationary targets, and moving targets,
both on planar surfaces. Monte-Carlo simulations demonstrate the advantages of Lévy over the lawnmower
strategy especially for moving targets. Ultimately to corroborate the suitability of the Lévy strategy for UAVs,
we implement and demonstrate the feasibility of the algorithm in the Multiple Unified Simulation Environment
(MUSE), which includes vehicle's constraints and dynamics. The MUSE / Air Force Synthetic Environment for
Reconnaissance and Surveillance (AFSERS) simulation system is the primary virtual ISR and UAV simulation
within DOD for command and staff level training for the Joint Services.
Edge features are often used in computer vision for image exploitation algorithms. A method to extract edge
features that is robust to contrast change, translation, rotation, noise and scale change is presented. This method
consists of the following steps: decompose the image into it's level set shapes, smooth the shapes, locate sections
of the shape borders that have nearly constant curvature, and locate a key point based on these curve sections.
The level sets are found using the Fast Level Set Transform (FLST). An affine invariant smoothing technique was
then applied to the level set shape borders to reduce pixel effects and noise, and an intrinsic scale was estimated
from the level set borders. The final step was key point location and scale estimation using the Helmholtz
principle. These key points were found to be more resilient to large scale changes than the SIFT key points.
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.