Projects

Explainable Novel Category Discovery

Developing a framework for explainable category discovery in deep learning models, enabling the identification of novel categories and providing interpretable explanations for model predictions.

Interpretable and Efficient Transformer Architectures for Fine-Grained Within-Season Crop Mapping in South Dakota

Developing interpretable and efficient transformer architectures for fine-grained within-season crop mapping in South Dakota, leveraging remote sensing data to improve agricultural monitoring and decision-making.

Supported by Competitive Research Grant program hosted by the South Dakota Board of Regents