Congratulations to our labmates and collaborators: Joshua Peeples, Sarah Walker, Connor McCurley, Alina Zare, James Keller and Weihuang Xu! Their paper, “Divergence Regulated Encoder Network for Joint Dimensionality Reduction and Classification”, was recently accepted to IEEE Geoscience and Remote Sensing… Read More
Tag: deep convolutional neural networks
Congratulations to Yiming Cui for a Successful Proposal Defense!
Congratulations to our labmate Yiming Cui for successfully defending his research proposal! Defending an oral research proposal is the second of four milestones to completing a Ph.D. at the University of Florida. Yiming is planning to conduct point cloud semantic… Read More
Histogram Layers For Texture Analysis
Abstract: We present a histogram layer for artificial neural networks (ANNs). An essential aspect of texture analysis is the extraction of features that describe the distribution of values in local spatial regions. The proposed histogram layer directly computes the spatial… Read More
Congratulations to Xiaolei Guo for becoming a PhD candidate!
Congratulations to our labmate, Xiaolei Guo, for passing her Oral Qualifying Exam and becoming a PhD candidate! For the remainder of her PhD work, Xiaolei plans to investigate fundamental research questions on “Interactive Segmentation with Deep Metric Learning”. We are… Read More
WALKER PRESENTS AT UF 2021 UNDERGRADUATE RESEARCH SYMPOSIUM!
Congratulations to our labmate, Sarah Walker! Sarah presented her work, titled “Divergence Regulated Encoder Network for Joint Dimensionality Reduction and Classification” at UF’s 2021 Undergraduate Research Virtual Symposium. The virtual symposium featured outstanding undergraduate researchers across all colleges at UF.… Read More
DIVERGENCE REGULATED ENCODER NETWORK FOR JOINT DIMENSIONALITY REDUCTION AND CLASSIFICATION
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… Read More
EXPLAINABLE SAS ACCEPTED TO IGARSS!
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… Read More
EXPLAINABLE SYSTEMATIC ANALYSIS FOR SYNTHETIC APERTURE SONAR IMAGERY
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… Read More
ZARE PRESENTED IN UFII AI ADVANCES SEMINAR!
Dr. Alina Zare recently presented in the University of Florida Informatics Institute’s virtual seminar on AI Advances and Applications. During her talk, Alina discussed how the Machine Learning and Sensing Lab is using AI methods to advance the understanding… Read More
SUPER RESOLUTION FOR ROOT IMAGING PUBLISHED IN APPS!
Congratulations to our labmates Jose Ruiz-Munoz and Alina Zare as well as collaborators Jyothier Nimmagadda, Tyler Dowd and James Baciak! Their paper, titled “Super Resolution for Root Imaging”, was recently published to Applications in Plant Sciences (APPS). If you’re interested… Read More