High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks


Abstract in English

We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN). We first notice CNNs ability in capturing the high-frequency components of images. These high-frequency components are almost imperceptible to a human. Thus the observation leads to multiple hypotheses that are related to the generalization behaviors of CNN, including a potential explanation for adversarial examples, a discussion of CNNs trade-off between robustness and accuracy, and some evidence in understanding training heuristics.

Download