This event will be held virtually.
Speaker: Koushik Nagasubramanian, ECpE Graduate Student
Advisors: Baskar Ganapathysubramanian and Soumik Sarkar
Title: Machine Learning for Image-based Plant Phenotyping
Abstract: Deep learning approaches have been successfully deployed for a diverse array of image-based plant phenotyping applications. However, successful deployment of supervised deep learning models requires large amount of labeled data, which is a significant challenge in plant science (and most biological) domains due to the inherent complexity. Specifically, collection and annotation of relevant data is a costly, laborious, time consuming and might need domain expertise. In this talk, I will summarize about the usefulness of domain adaptation, active learning, and local explanation techniques for plant phenotyping applications. I will focus on how these methods can be used to overcome the distribution shift, data annotation and interpretability challenges in applying deep learning models to Maize and Soybean phenotyping tasks.
Bio: Koushik Nagasubramanian is currently a fifth year PhD student in the Electrical Engineering department at Iowa State University. He works under the joint supervision of Prof. Baskar Ganapathysubramanian and Prof. Soumik Sarkar. His research focuses on deep learning applications in plant phenotyping. He was a visiting student at U.Tokyo International Field Phenomics Research Lab and a data science intern at Corteva Agriscience in 2019.
Webinar Link: https://iastate.webex.com/iastate/j.php?MTID=mb128a187c5d48a06c5fa2a0545562b93