Imaging Science Ph.D. Defense: Aneesh Rangnekar
Ph.D. Dissertation Defense
Learning representations in the hyperspectral domain in aerial imagery
Imaging Science Ph.D. Candidate
Chester F. Carlson Center for Imaging Science, RIT
Register Here for Zoom Link
We explore learning representations that help perform object detection and segmentation tasks in hyperspectral imagery. In addition, we also explore the area of learning with limited data and leverage two machine learning frameworks, semi-supervised learning, and active learning to help improve the learning capability of neural networks. There are hardly any datasets present for performing object detection or segmentation in hyperspectral imagery – for this reason, we gather, annotate and release three datasets, AeroRIT, RooftopHSI, and ROCEyes, with two sets of baselines – the first baseline consists of dealing with all labeled data and the second baseline deals with learning under limited data availability.
Undergraduates, graduates, and experts. Those with interest in the topic.
To request an interpreter, please visit https://myaccess.rit.edu
When and Where
Open to the Public