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.

翻译：深度卷积神经网络（CNN）极大推动了大规模图像分类的最新进展。近期，基于胶囊（神经元群）的动态路由算法展现了最先进的识别性能。然而，此类网络在退化信号（噪声）干扰下的行为特性仍鲜有研究。针对不同网络架构的噪声鲁棒性进行系统分析，对于在特定应用场景中选择合适模型至关重要。本文对六种常见图像退化模型下，六种深度学习架构的图像分类性能进行了全面分析。本研究分别比较了VGG-16、VGG-19、ResNet-50、Inception-v3、MobileNet和CapsuleNet架构在高斯白噪声、高斯彩色噪声、椒盐噪声、高斯模糊、运动模糊及JPEG压缩噪声模型中的表现。