Improving Corruption Robustness with Random Erasing in the Frequency Domain

Abstract

This study introduces a new data augmentation method to improve the corruption robustness of the convolutional neural network (CNN). Many data augmentation methods have been studied to reduce overfitting and to improve the generalization ability of CNNs. One of the most widely used data augmentation techniques is Random Erasing which erases a random rectangle region of an image. Most of the augmentation methods are applied in the spatial domain, but augmentation techniques in the frequency domain are less studied. In this study, the image is processed with 2D discrete Fourier transform (DFT), and then Random Erasing is applied in the frequency domain. Finally, the inversed image generated with inverse DFT is used as an input. As a result, the proposed method leads to the robustness improvement of the model against common corruptions.