Effects of Degradations on Deep Neural Network Architectures
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2018
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915155701399552 |
|---|---|
| author | Roy, Prasun Ghosh, Subhankar Bhattacharya, Saumik Pal, Umapada |
| author_facet | Roy, Prasun Ghosh, Subhankar Bhattacharya, Saumik Pal, Umapada |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1807_10108 |
| institution | arXiv |
| publishDate | 2018 |
| record_format | arxiv |
| spellingShingle | Effects of Degradations on Deep Neural Network Architectures Roy, Prasun Ghosh, Subhankar Bhattacharya, Saumik Pal, Umapada Computer Vision and Pattern Recognition Image and Video Processing 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. |
| title | Effects of Degradations on Deep Neural Network Architectures |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/1807.10108 |