Team Members: Kassi Nzalasse and Eli Laird
Our research focuses on advancing face recognition systems through the use of synthetic data. We're developing a comprehensive pipeline to generate synthetic facial images and leverage this data to train and evaluate face recognition models.
Our work has two primary objectives: first, to explore the potential of synthetic data in enhancing the training process of face recognition systems, potentially addressing issues of data scarcity and privacy concerns associated with real-world datasets. Second, we're creating targeted synthetic evaluation datasets to rigorously benchmark these systems and uncover potential biases. This dual approach allows us to investigate the efficacy of synthetic data in improving model performance while developing more robust and fair evaluation methodologies.