Search Results for author: Alina Zare

Found 43 papers, 13 papers with code

Shared Manifold Learning Using a Triplet Network for Multiple Sensor Translation and Fusion with Missing Data

no code implementations25 Oct 2022 Aditya Dutt, Alina Zare, Paul Gader

In this paper, we propose a Contrastive learning based MultiModal Alignment Network (CoMMANet) to align data from different sensors into a shared and discriminative manifold where class information is preserved.

Contrastive Learning

Histogram Layers for Synthetic Aperture Sonar Imagery

no code implementations8 Sep 2022 Joshua Peeples, Alina Zare, Jeffrey Dale, James Keller

Synthetic aperture sonar (SAS) imagery is crucial for several applications, including target recognition and environmental segmentation.

Image-to-Height Domain Translation for Synthetic Aperture Sonar

no code implementations12 Dec 2021 Dylan Stewart, Shawn Johnson, Alina Zare

The low grazing angle of the collection geometry, combined with orientation of the sonar path relative to anisotropic texture, poses a significant challenge for image-alignment and other multi-view scene understanding frameworks.

Scene Understanding Translation

Cross-Layered Distributed Data-driven Framework For Enhanced Smart Grid Cyber-Physical Security

no code implementations10 Nov 2021 Allen Starke, Keerthiraj Nagaraj, Cody Ruben, Nader Aljohani, Sheng Zou, Arturo Bretas, Janise McNair, Alina Zare

Smart Grid (SG) research and development has drawn much attention from academia, industry and government due to the great impact it will have on society, economics and the environment.

Anomaly Detection

Robust Semi-Supervised Classification using GANs with Self-Organizing Maps

no code implementations19 Oct 2021 Ronald Fick, Paul Gader, Alina Zare

The problem of discriminating outliers from inliers while maintaining classification accuracy is referred to here as the DOIC problem.


Possibilistic Fuzzy Local Information C-Means with Automated Feature Selection for Seafloor Segmentation

no code implementations14 Oct 2021 Joshua Peeples, Daniel Suen, Alina Zare, James Keller

The chosen features and resulting segmentation from the image will be assessed based on a select quantitative clustering validity criterion and the subset of the features that reach a desired threshold will be used for the segmentation process.

Clustering feature selection +2

The Weakly-Labeled Rand Index

no code implementations8 Mar 2021 Dylan Stewart, Anna Hampton, Alina Zare, Jeff Dale, James Keller

In this paper, a labeling approach and associated modified version of the Rand index for weakly-labeled data is introduced to address these issues.

Explainable Systematic Analysis for Synthetic Aperture Sonar Imagery

no code implementations6 Jan 2021 Sarah Walker, Joshua Peeples, Jeff Dale, James Keller, Alina Zare

In this work, we present an in-depth and systematic analysis using tools such as local interpretable model-agnostic explanations (LIME) (arXiv:1602. 04938) and divergence measures to analyze what changes lead to improvement in performance in fine tuned models for synthetic aperture sonar (SAS) data.

Classification General Classification +1

Divergence Regulated Encoder Network for Joint Dimensionality Reduction and Classification

1 code implementation31 Dec 2020 Joshua Peeples, Sarah Walker, Connor McCurley, Alina Zare, James Keller, Weihuang Xu

In order to better represent statistical texture information for remote-sensing image classification, in this paper, we investigate performing joint dimensionality reduction and classification using a novel histogram neural network.

Classification Dimensionality Reduction +3

Weakly Supervised Minirhizotron Image Segmentation with MIL-CAM

no code implementations30 Jul 2020 Guohao Yu, Alina Zare, Weihuang Xu, Roser Matamala, Joel Reyes-Cabrera, Felix B. Fritschi, Thomas E. Juenger

The proposed approach outperforms other attention map and multiple instance learning methods for localization of root objects in minirhizotron imagery.

Image Segmentation Multiple Instance Learning +1

Outlier Detection through Null Space Analysis of Neural Networks

no code implementations2 Jul 2020 Matthew Cook, Alina Zare, Paul Gader

Specifically, many systems lack the ability to identify when outliers (e. g., samples that are distinct from and not represented in the training data distribution) are being presented to the system.

Classification General Classification +1

Super Resolution for Root Imaging

1 code implementation30 Mar 2020 Jose F. Ruiz-Munoz, Jyothier K. Nimmagadda, Tyler G. Dowd, James E. Baciak, Alina Zare

High-resolution cameras have become very helpful for plant phenotyping by providing a mechanism for tasks such as target versus background discrimination, and the measurement and analysis of fine-above-ground plant attributes.

Image Enhancement Plant Phenotyping +1

Spectral Variability in Hyperspectral Data Unmixing: A Comprehensive Review

no code implementations21 Jan 2020 Ricardo Augusto Borsoi, Tales Imbiriba, José Carlos Moreira Bermudez, Cédric Richard, Jocelyn Chanussot, Lucas. Drumetz, Jean-Yves Tourneret, Alina Zare, Christian Jutten

The spectral signatures of the materials contained in hyperspectral images, also called endmembers (EM), can be significantly affected by variations in atmospheric, illumination or environmental conditions typically occurring within an image.

Histogram Layers for Texture Analysis

2 code implementations1 Jan 2020 Joshua Peeples, Weihuang Xu, Alina Zare

We present a histogram layer for artificial neural networks (ANNs).

Texture Classification

Peanut Maturity Classification using Hyperspectral Imagery

no code implementations20 Oct 2019 Sheng Zou, Yu-Chien Tseng, Alina Zare, Diane Rowland, Barry Tillman, Seung-Chul Yoon

The maturity assessment process involves the removal of the exocarp of the hull and visually categorizing the mesocarp color into varying color classes from immature (white, yellow, orange) to mature (brown, and black).

Classification General Classification

Multi-Target Multiple Instance Learning for Hyperspectral Target Detection

1 code implementation7 Sep 2019 Susan Meerdink, James Bocinsky, Alina Zare, Nicholas Kroeger, Connor McCurley, Daniel Shats, Paul Gader

They learn a dictionary of target signatures that optimizes detection against a background using the Adaptive Cosine Estimator (ACE) and Spectral Match Filter (SMF).

Multiple Instance Learning

Investigation of Initialization Strategies for the Multiple Instance Adaptive Cosine Estimator

no code implementations30 Apr 2019 James Bocinsky, Connor McCurley, Daniel Shats, Alina Zare

Sensors which use electromagnetic induction (EMI) to excite a response in conducting bodies have long been investigated for subsurface explosive hazard detection.

Comparison of Hand-held WEMI Target Detection Algorithms

no code implementations22 Mar 2019 Connor H. McCurley, James Bocinsky, Alina Zare

Wide-band Electromagnetic Induction Sensors (WEMI) have been used for a number of years in subsurface detection of explosive hazards.

Overcoming Small Minirhizotron Datasets Using Transfer Learning

1 code implementation22 Mar 2019 Weihuang Xu, Guohao Yu, Alina Zare, Brendan Zurweller, Diane Rowland, Joel Reyes-Cabrera, Felix B. Fritschi, Roser Matamala, Thomas E. Juenger

A key component of automated analysis of plant roots from imagery is the automated pixel-level segmentation of roots from their surrounding soil.

Transfer Learning

Root Identification in Minirhizotron Imagery with Multiple Instance Learning

1 code implementation7 Mar 2019 Guohao Yu, Alina Zare, Hudanyun Sheng, Roser Matamala, Joel Reyes-Cabrera, Felix B. Fritschi, Thomas E. Juenger

In this paper, multiple instance learning (MIL) algorithms to automatically perform root detection and segmentation in minirhizotron imagery using only image-level labels are proposed.

Multiple Instance Learning

Multiple Instance Choquet Integral Classifier Fusion and Regression for Remote Sensing Applications

1 code implementation11 Mar 2018 Xiaoxiao Du, Alina Zare

In classifier (or regression) fusion the aim is to combine the outputs of several algorithms to boost overall performance.

Crop Yield Prediction General Classification +2

Multiple Instance Hybrid Estimator for Hyperspectral Target Characterization and Sub-pixel Target Detection

no code implementations31 Oct 2017 Changzhe Jiao, Chao Chen, Ronald G. McGarvey, Stephanie Bohlman, Licheng Jiao, Alina Zare

The Multiple Instance Hybrid Estimator for discriminative target characterization from imprecisely labeled hyperspectral data is presented.

Multiple Instance Learning

Multiple Instance Dictionary Learning for Beat-to-Beat Heart Rate Monitoring from Ballistocardiograms

no code implementations11 Jun 2017 Changzhe Jiao, Bo-Yu Su, Princess Lyons, Alina Zare, K. C. Ho, Marjorie Skubic

A multiple instance dictionary learning approach, Dictionary Learning using Functions of Multiple Instances (DL-FUMI), is used to perform beat-to-beat heart rate estimation and to characterize heartbeat signatures from ballistocardiogram (BCG) signals collected with a hydraulic bed sensor.

Dictionary Learning Heart rate estimation +1

Hyperspectral Unmixing with Endmember Variability using Semi-supervised Partial Membership Latent Dirichlet Allocation

no code implementations17 Mar 2017 Sheng Zou, Hao Sun, Alina Zare

A semi-supervised Partial Membership Latent Dirichlet Allocation approach is developed for hyperspectral unmixing and endmember estimation while accounting for spectral variability and spatial information.

Hyperspectral Unmixing

Multiple Instance Hybrid Estimator for Learning Target Signatures

no code implementations9 Jan 2017 Changzhe Jiao, Alina Zare

Both simulated and real hyperspectral target detection experiments are shown to illustrate the effectiveness of the method.

Multiple Instance Learning

Map-guided Hyperspectral Image Superpixel Segmentation Using Proportion Maps

no code implementations6 Jan 2017 Hao Sun, Alina Zare

A map-guided superpixel segmentation method for hyperspectral imagery is developed and introduced.

Partial Membership Latent Dirichlet Allocation

2 code implementations28 Dec 2016 Chao Chen, Alina Zare, Huy Trinh, Gbeng Omotara, J. Tory Cobb, Timotius Lagaunne

Topic models (e. g., pLSA, LDA, sLDA) have been widely used for segmenting imagery.

Topic Models

Hyperspectral Unmixing with Endmember Variability using Partial Membership Latent Dirichlet Allocation

no code implementations12 Sep 2016 Sheng Zou, Alina Zare

The application of Partial Membership Latent Dirichlet Allocation(PM-LDA) for hyperspectral endmember estimation and spectral unmixing is presented.

Hyperspectral image analysis Hyperspectral Unmixing

Multiple Instance Hyperspectral Target Characterization

1 code implementation20 Jun 2016 Alina Zare, Changzhe Jiao, Taylor Glenn

In this paper, two methods for multiple instance target characterization, MI-SMF and MI-ACE, are presented.

Instance Influence Estimation for Hyperspectral Target Signature Characterization using Extended Functions of Multiple Instances

no code implementations21 Mar 2016 Sheng Zou, Alina Zare

From these imprecise labels, eFUMI has been shown to be effective at estimating target signatures in hyperspectral subpixel target detection problems.

Multiple Instance Learning

Adaptive coherence estimator (ACE) for explosive hazard detection using wideband electromagnetic induction (WEMI)

no code implementations19 Mar 2016 Brendan Alvey, Alina Zare, Matthew Cook, Dominic K. Ho

The adaptive coherence estimator (ACE) estimates the squared cosine of the angle between a known target vector and a sample vector in a whitened coordinate space.

Buried object detection using handheld WEMI with task-driven extended functions of multiple instances

no code implementations19 Mar 2016 Matthew Cook, Alina Zare, Dominic Ho

The new algorithm, Task Driven Extended Functions of Multiple Instances, can overcome data that does not have very precise point-wise labels and still learn a highly discriminative dictionary.

Dictionary Learning object-detection +1

Partial Membership Latent Dirichlet Allocation

2 code implementations9 Nov 2015 Chao Chen, Alina Zare, J. Tory Cobb

Topic models (e. g., pLSA, LDA, SLDA) have been widely used for segmenting imagery.

Topic Models

Multiple Instance Dictionary Learning using Functions of Multiple Instances

2 code implementations9 Nov 2015 Changzhe Jiao, Alina Zare

A multiple instance dictionary learning method using functions of multiple instances (DL-FUMI) is proposed to address target detection and two-class classification problems with inaccurate training labels.

Dictionary Learning General Classification +1

Estimating Target Signatures with Diverse Density

no code implementations30 Oct 2015 Taylor Glenn, Alina Zare

Hyperspectral target detection algorithms rely on knowing the desired target signature in advance.

Multiple Instance Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.