High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

H. Wang, X. Wu, Z. Huang, and E. P. Xing. "High frequency component helps explain the generalization of convolutional neural networks." CVPR 2020 (Oral).

[Slides] and [Poster]

Highlights

Fig. 1: The central hypothesis of our paper: within a data collection, there are correlations between the highfrequency components and the “semantic” component of the images. As a result, the model will perceive both high-frequency components as well as the “semantic” ones, leading to generalization behaviors counterintuitive to human (e.g., adversarial examples).

Fig. 2: Eight testing samples selected from CIFAR10 that help explain that CNN can capture the high-frequency image: the model (ResNet18) correctly predicts the original image (1st column in each panel) and the high frequency reconstructed image (3rd column in each panel), but incorrectly predict the low-frequency reconstructed image (2nd column in each panel). The prediction confidences are also shown. Details are in the paper.

Code Structures

• scripts/resnet.py
  • Pipeline to replicate our results on CIFAR10 data
• utility/
  • attackHelper.py
    • main methods used to generate adversarial examples
  • dataLoader.py
    • load data
  • frequencyHelper.py
    • generate low and high frequency data
  • pdg_attack.py
    • helper for adversarial training

Before using the code

• Install the main dependency: TensorFlow 1.x and Foolbox
• Read the main script. We recommend users to skim through the script befoure usage. We use "todo" to highlight the parts that may require attention.
• Generate data: one can generate the data with utility/frequencyHelper.py

PyTorch Implementation

The results were generated by the TensorFlow code as shared here, but for the friends who prefer PyTorch, Xindi has nicely created some codes to help you start: PyTorch Implementation

Contact

HaohanWang · Xindi Wu · Zeyi Huang