Supplementary Materia: Revisiting Visual Model Robustness: A Frequency Long-Tailed Distribution View Zhiyu Lin

Previous research has provided many intriguing insights into model robustness through the lens of frequency spectrum for the Deep Learning (DL) community. Many of these studies attempted to elucidate the connection between model sensitivity and frequency components. A commonly-held hypothesis is that the utilization of high-frequency components leads to a decrease in model robustnessWang et al. [2020]. Recent research has improved model robustness through a variety of methods, guided by this hypothesis. For example, Addepalli et al. [2022] applies regularization terms to high-frequency components to enhance model robustness.