On the Performance of Convolutional Neural Networks under High and Low Frequency Information

TL;DR

This paper investigates CNN performance on high and low frequency image components, revealing limitations in generalization, and proposes a stochastic filtering data augmentation method to enhance robustness across frequencies.

Contribution

It introduces a stochastic filtering based data augmentation technique to improve CNN robustness to high and low frequency image information.

Findings

CNN models struggle to generalize over high and low frequency images.

Stochastic filtering augmentation improves frequency-based robustness.

Experiments show performance gains on CIFAR-10 and Tiny-ImageNet datasets.

Abstract

Convolutional neural networks (CNNs) have shown very promising performance in recent years for different problems, including object recognition, face recognition, medical image analysis, etc. However, generally the trained CNN models are tested over the test set which is very similar to the trained set. The generalizability and robustness of the CNN models are very important aspects to make it to work for the unseen data. In this letter, we study the performance of CNN models over the high and low frequency information of the images. We observe that the trained CNN fails to generalize over the high and low frequency images. In order to make the CNN robust against high and low frequency images, we propose the stochastic filtering based data augmentation during training. A satisfactory performance improvement has been observed in terms of the high and low frequency generalization and robustness with the proposed stochastic filtering based data augmentation approach. The experimentations are performed using ResNet50 model over the CIFAR-10 dataset and ResNet101 model over Tiny-ImageNet dataset.