Category: News

Abstract: In this paper, we investigate performing joint dimensionality reduction and classification using a novel histogram neural network. Motivated by a popular dimensionality reduction approach, t-Distributed Stochastic Neighbor Embedding (t-SNE), our proposed method incorporates a classification loss computed on samples in a low-dimensional embedding space. We compare the learned sample embeddings against coordinates found by […]

Congratulations to Gatorsense alumnus, Daniel Suen!   Daniel was recently awarded a Graduate Research Fellowship by the National Science Foundation to fund his Ph.D. work in Statistics at the University of Washington.    We are so proud of you, Daniel.  Keep up the great work!  

Congratulations to our labmates and collaborators: Diandra Prioleau, Kiana Alikhademi, Armisha Roberts, Joshua Peeples, Alina Zare and Juan Gilbert!  Their paper, “Application of Divisive Clustering for Reducing Bias in Imbalanced Data” was recently accepted to the the 2021 International Conference on Machine Learning and Data Mining (MLDM). In their paper, the authors propose the use […]

Abstract: A lack of diversity and representativeness within training data causes bias in the machine learning pipeline by influencing the performance of many machine learning models to favor the majority of samples that are most similar. It is necessary to have diverse and representative training data, especially for application domains in which people of varying […]

Congratulations to Dr. Sheng Zou for graduating with his Ph.D.! Sheng’s dissertation is titled “Classification with Multi-Imprecise Labels.” His research focused on developing classification approaches under the multiple instance learning framework. The goal of Sheng’s work was to model class variability using discriminative probabilistic distributions and multiple types of imprecise labels. Read about more Sheng’s […]

Congratulations to our labmates: Sarah Walker, Joshua Peeples, Jeff Dale, James Keller and Alina Zare!  Their paper, “Explainable Systematic Analysis for Synthetic Aperture Sonar Imagery” was recently accepted to the IEEE International Geoscience and Remote Sensing Symposium (IGARSS). In their paper, the authors provide an in-depth analysis to the factors that affect performance of texture […]

Congratulations to our labmates: Dylan Stewart, Anna Hampton, Alina Zare, Jeff Dale and James Keller!  Their paper, “The Weakly-Labeled Rand Index” was recently accepted to the IEEE International Geoscience and Remote Sensing Symposium (IGARSS). In their paper, the authors introduce an approach to quantify superpixel segmentation performance. Whereas traditional evaluation approaches require crisp segmentations, the […]

Abstract: In this work, we present an in-depth and systematic analysis using tools such as local interpretable model-agnostic explanations (LIME) and divergence measures to analyze what changes lead to improvement in performance in fine tuned models for synthetic aperture sonar (SAS) data. We examine the sensitivity to factors in the fine tuning process such as […]

Abstract: Synthetic Aperture Sonar (SAS) surveys produce imagery with large regions of transition between seabed types. Due to these regions, it is difficult to label and segment the imagery and, furthermore, challenging to score the image segmentations appropriately. While there are many approaches to quantify performance in standard crisp segmentation schemes, drawing hard boundaries in […]

Congratulations to our labmate, Connor McCurley, for passing his oral qualifying exam and becoming a PhD candidate!  For the remainder of his Ph.D. work, Connor plans to investigate “Discriminative Manifold Embedding with Imprecise, Uncertain and Ambiguous Data.” Great work, Connor!