Search Results - "Doster, Timothy"
-
1
De-multiplexing vortex modes in optical communications using transport-based pattern recognition
Published in Optics express (19-02-2018)“…Free space optical communications utilizing orbital angular momentum beams have recently emerged as a new technique for communications with potential for…”
Get full text
Journal Article -
2
Path-Based Dictionary Augmentation: A Framework for Improving [Formula Omitted]-Sparse Image Processing
Published in IEEE transactions on image processing (01-01-2020)“…We have previously shown that augmenting orthogonal matching pursuit (OMP) with an additional step in the identification stage of each pursuit iteration yields…”
Get full text
Journal Article -
3
Path-Based Dictionary Augmentation: A Framework for Improving k -Sparse Image Processing
Published in IEEE transactions on image processing (2020)“…We have previously shown that augmenting orthogonal matching pursuit (OMP) with an additional step in the identification stage of each pursuit iteration yields…”
Get full text
Journal Article -
4
Gradual DropIn of Layers to Train Very Deep Neural Networks
Published in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2016)“…We introduce the concept of dynamically growing a neural network during training. In particular, an untrainable deep network starts as a trainable shallow…”
Get full text
Conference Proceeding -
5
Spatial-spectral operator theoretic methods for hyperspectral image classification
Published in GEM international journal on geomathematics (01-11-2016)“…With the emergence of new remote sensing modalities, it becomes increasingly important to find novel algorithms for fusion and integration of different types…”
Get full text
Journal Article -
6
Reproducing Kernel Hilbert Space Pruning for Sparse Hyperspectral Abundance Prediction
Published 16-08-2023“…Hyperspectral measurements from long range sensors can give a detailed picture of the items, materials, and chemicals in a scene but analysis can be difficult,…”
Get full text
Journal Article -
7
A case study on data fusion with overlapping segments
Published in 2013 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) (01-10-2013)“…With the continual improvement and diversification of existing sensing modalities and the emergence of new sensing technologies, methods to effectively and…”
Get full text
Conference Proceeding -
8
Data-Driven Invertible Neural Surrogates of Atmospheric Transmission
Published in IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium (07-07-2024)“…We present a framework for inferring an atmospheric transmission profile from a spectral scene. This framework leverages a lightweight, physics-based simulator…”
Get full text
Conference Proceeding -
9
Data-Driven Invertible Neural Surrogates of Atmospheric Transmission
Published 30-04-2024“…We present a framework for inferring an atmospheric transmission profile from a spectral scene. This framework leverages a lightweight, physics-based simulator…”
Get full text
Journal Article -
10
STARS: Sensor-agnostic Transformer Architecture for Remote Sensing
Published 08-11-2024“…We present a sensor-agnostic spectral transformer as the basis for spectral foundation models. To that end, we introduce a Universal Spectral Representation…”
Get full text
Journal Article -
11
Harmonic analysis inspired data fusion for applications in remote sensing
Published 01-01-2014“…This thesis will address the fusion of multiple data sources arising in remote sensing, such as hyperspectral and LIDAR. Fusing of multiple data sources…”
Get full text
Dissertation -
12
A Novel Detection Paradigm and Its Comparison to Statistical and Kernel-Based Anomaly Detection Algorithms for Hyperspectral Imagery
Published in 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01-07-2017)“…Detection of anomalous pixels within hyperspectral imagery is frequently used for purposes ranging from the location of invasive plant species to the detection…”
Get full text
Conference Proceeding -
13
Reward-Free Attacks in Multi-Agent Reinforcement Learning
Published 01-12-2021“…We investigate how effective an attacker can be when it only learns from its victim's actions, without access to the victim's reward. In this work, we are…”
Get full text
Journal Article -
14
In What Ways Are Deep Neural Networks Invariant and How Should We Measure This?
Published 07-10-2022“…It is often said that a deep learning model is "invariant" to some specific type of transformation. However, what is meant by this statement strongly depends…”
Get full text
Journal Article -
15
Path Orthogonal Matching Pursuit for k-Sparse Image Reconstruction
Published in 2018 26th European Signal Processing Conference (EUSIPCO) (01-09-2018)“…We introduce a path-augmentation step to the standard orthogonal matching pursuit algorithm. Our augmentation may be applied to any algorithm that relies on…”
Get full text
Conference Proceeding -
16
OAM channel efficiency in the presence of turbulence for Laguerre- and Bessel-Gauss beams
Published in 2016 Conference on Lasers and Electro-Optics (CLEO) (01-06-2016)“…Bessel-Gauss beams, a type of pseudo non-diffracting beam, are examined for their robustness for propagation through turbulent free space and compared to…”
Get full text
Conference Proceeding -
17
Path Orthogonal Matching Pursuit for Sparse Reconstruction and Denoising of SWIR Maritime Imagery
Published in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01-06-2018)“…We introduce an extension that may be used to augment algorithms used for the sparse decomposition of signals into a linear combination of atoms drawn from a…”
Get full text
Conference Proceeding -
18
Con Connections: Detecting Fraud from Abstracts using Topological Data Analysis
Published in 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) (01-12-2021)“…In this paper we present a novel approach for identifying fraudulent papers from their titles and abstracts. The premise of the approach is that there are…”
Get full text
Conference Proceeding -
19
Rotational Equivariance for Object Classification Using xView
Published in IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium (26-09-2020)“…With the recent addition of large, curated and labeled data sets to the remote sensing discipline, deep learning models have largely surpassed the performance…”
Get full text
Conference Proceeding -
20
Argumentative Topology: Finding Loop(holes) in Logic
Published 17-11-2020“…Advances in natural language processing have resulted in increased capabilities with respect to multiple tasks. One of the possible causes of the observed…”
Get full text
Journal Article