ML Anthology

High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

Haohan Wang, Xindi Wu, Zeyi Huang, Eric P. Xing
CVPR 2020
doi:10.1109/CVPR42600.2020.00871 /cvpr/2020/wang2020cvpr-highfrequency/

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.

PDF CVPR Semantic Scholar

Cite

Text

Wang et al. "High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00871

Markdown

[Wang et al. "High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/wang2020cvpr-highfrequency/) doi:10.1109/CVPR42600.2020.00871

BibTeX

@inproceedings{wang2020cvpr-highfrequency,
  title     = {{High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks}},
  author    = {Wang, Haohan and Wu, Xindi and Huang, Zeyi and Xing, Eric P.},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2020},
  doi       = {10.1109/CVPR42600.2020.00871},
  url       = {https://mlanthology.org/cvpr/2020/wang2020cvpr-highfrequency/}
}