Robust Learning with Frequency Domain Regularization

07/07/2020
by   Weiyu Guo, et al.
0

Convolution neural networks have achieved remarkable performance in many tasks of computing vision. However, CNN tends to bias to low frequency components. They prioritize capturing low frequency patterns which lead them fail when suffering from application scenario transformation. While adversarial example implies the model is very sensitive to high frequency perturbations. In this paper, we introduce a new regularization method by constraining the frequency spectra of the filter of the model. Different from band-limit training, our method considers the valid frequency range probably entangles in different layers rather than continuous and trains the valid frequency range end-to-end by backpropagation. We demonstrate the effectiveness of our regularization by (1) defensing to adversarial perturbations; (2) reducing the generalization gap in different architecture; (3) improving the generalization ability in transfer learning scenario without fine-tune.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/09/2022

How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?

Model robustness is vital for the reliable deployment of machine learnin...
research
02/28/2019

On the Effectiveness of Low Frequency Perturbations

Carefully crafted, often imperceptible, adversarial perturbations have b...
research
05/28/2019

High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

We investigate the relationship between the frequency spectrum of image ...
research
12/24/2022

Frequency Regularization for Improving Adversarial Robustness

Deep neural networks are incredibly vulnerable to crafted, human-imperce...
research
04/03/2022

Improving Vision Transformers by Revisiting High-frequency Components

The transformer models have shown promising effectiveness in dealing wit...
research
06/19/2022

JPEG Compression-Resistant Low-Mid Adversarial Perturbation against Unauthorized Face Recognition System

It has been observed that the unauthorized use of face recognition syste...
research
05/29/2019

Learning Robust Global Representations by Penalizing Local Predictive Power

Despite their renowned predictive power on i.i.d. data, convolutional ne...

Please sign up or login with your details

Forgot password? Click here to reset