Effects of Degradations on Deep Neural Network Architectures
This work addresses the problem of selecting appropriate deep learning models for image classification in noisy conditions, which is incremental as it extends existing architectures to new degradation scenarios.
The paper analyzed the robustness of six deep neural network architectures, including VGG-16, VGG-19, ResNet-50, Inception-v3, MobileNet, and CapsuleNet, against six common image degradation models such as Gaussian white noise and JPEG compression, to guide model selection in noisy environments.
Deep convolutional neural networks (CNN) have massively influenced recent advances in large-scale image classification. More recently, a dynamic routing algorithm with capsules (groups of neurons) has shown state-of-the-art recognition performance. However, the behavior of such networks in the presence of a degrading signal (noise) is mostly unexplored. An analytical study on different network architectures toward noise robustness is essential for selecting the appropriate model in a specific application scenario. This paper presents an extensive performance analysis of six deep architectures for image classification on six most common image degradation models. In this study, we have compared VGG-16, VGG-19, ResNet-50, Inception-v3, MobileNet and CapsuleNet architectures on Gaussian white, Gaussian color, salt-and-pepper, Gaussian blur, motion blur and JPEG compression noise models.