Effects of Degradations on Deep Neural Network Architectures

Abstract

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.

10 pages

References in corpus (2)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Cited by in corpus (15)

• Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
• Deep learning for multimessenger core-collapse supernova detection
• Distributed Learning and Inference with Compressed Images
• Co-VeGAN: Complex-Valued Generative Adversarial Network for Compressive Sensing MR Image Reconstruction
• A Novel lightweight Convolutional Neural Network, ExquisiteNetV2
• Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
• A Possible Reason for why Data-Driven Beats Theory-Driven Computer Vision
• Deep Network Ensemble Learning applied to Image Classification using CNN Trees
• Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
• AQuA: Analytical Quality Assessment for Optimizing Video Analytics Systems
• Geometric feature performance under downsampling for EEG classification tasks
• Cross-Domain Image Classification through Neural-Style Transfer Data Augmentation
• Learning degraded image classification with restoration data fidelity
• Extracting Interpretable Concept-Based Decision Trees from CNNs
• Online Continual Learning in Image Classification: An Empirical Survey