1 code implementation • 25 Apr 2024 • Akshatha Mohan, Joshua Peeples
This work contributes to the evolving landscape of artificial neural network architectures by introducing a novel pooling layer that enriches the representation of spatial features.
1 code implementation • 25 Mar 2024 • Joshua Peeples, Salim Al Kharsa, Luke Saleh, Alina Zare
These engineered features include local binary patterns and edge histogram descriptors among others and they have been shown to be informative features for a variety of computer vision tasks.
1 code implementation • 25 Jul 2023 • Jarin Ritu, Ethan Barnes, Riley Martell, Alexandra Van Dine, Joshua Peeples
In this work, a novel method combines a time delay neural network and histogram layer to incorporate statistical contexts for improved feature learning and underwater acoustic target classification.
1 code implementation • 6 Jun 2023 • Akshatha Mohan, Joshua Peeples
We present a comprehensive analysis of quantitatively evaluating explainable artificial intelligence (XAI) techniques for remote sensing image classification.
no code implementations • 8 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.
no code implementations • 14 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.
1 code implementation • 11 Oct 2021 • Joshua Peeples, Connor McCurley, Sarah Walker, Dylan Stewart, Alina Zare
We compare our LACE to alternative state-of-the art softmax-based and feature regularization approaches.
no code implementations • 6 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.
1 code implementation • 31 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.
2 code implementations • 1 Jan 2020 • Joshua Peeples, Weihuang Xu, Alina Zare
We present a histogram layer for artificial neural networks (ANNs).
no code implementations • 1 Apr 2019 • Joshua Peeples, Matthew Cook, Daniel Suen, Alina Zare, James Keller
In this paper, we compare the segmentation performance of a semi-supervised approach using PFLICM and a supervised method using Possibilistic K-NN.