June
2020
High-frequency component helps explain the generalization of convolutional neural networks
Authors:
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.
copied = false, 2000);
">
@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},
}
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},
}