High-frequency component helps explain the generalization of convolutional neural networks

June 2020

High-frequency component helps explain the generalization of convolutional neural networks

Authors:

Haohan Wang, Xindi Wu, Zeyi Huang, and Eric P. Xing
Conference Paper
Proceedings of (CVPR) Computer Vision and Pattern Recognition

Abstract:

We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN). We first notice CNN's 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 CNN's trade-off between robustness and accuracy, and some evidence in understanding training heuristics.
@conference{Wang-2020-126375,
author = {Haohan Wang And Xindi Wu And Zeyi Huang And Eric P. Xing},
title = {High-frequency component helps explain the generalization of convolutional neural networks},
booktitle = {Proceedings of (CVPR) Computer Vision and Pattern Recognition},
year = {2020},
month = {June},
pages = {8684 - 8694},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.