On the Performance of Convolutional Neural Networks under High and Low Frequency Information
This addresses the robustness problem for CNN users in applications like object recognition, but it is incremental as it builds on existing data augmentation techniques.
The study investigated the poor generalization of convolutional neural networks (CNNs) to high and low frequency images and proposed a stochastic filtering-based data augmentation method to improve robustness, resulting in satisfactory performance gains on CIFAR-10 and Tiny-ImageNet datasets.
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.