Quaternion Convolutional Neural Networks for Heterogeneous Image Processing
Convolutional neural networks (CNN) have recently achieved state-of-the-art results in various applications. In the case of image recognition, an ideal model has to learn independently of the training data, both local dependencies between the three components (R,G,B) of a pixel, and the global relations describing edges or shapes, making it efficient with small or heterogeneous datasets. Quaternion-valued convolutional neural networks (QCNN) solved this problematic by introducing multidimensional algebra to CNN. This paper proposes to explore the fundamental reason of the success of QCNN over CNN, by investigating the impact of the Hamilton product on a color image reconstruction task performed from a gray-scale only training. By learning independently both internal and external relations and with less parameters than real valued convolutional encoder-decoder (CAE), quaternion convolutional encoder-decoders (QCAE) perfectly reconstructed unseen color images while CAE produced worst and gray-scale versions.
Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Titouan Parcollet (add twitter)
Mohamed Morchid (add twitter)
Georges Linarès (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
1
Language:
Python
This repository is an update to all previous repositories with an implementation of various Quaternion-valued Neural Networks in PyTorch
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
11/07/18 06:05PM
3,164
1,234
Tweets
arxiv_cscv: Quaternion Convolutional Neural Networks for Heterogeneous Image Processing https://t.co/y6PYksnL5l
nmfeeds: [O] https://t.co/3XoEoBypKR Quaternion Convolutional Neural Networks for Heterogeneous Image Processing. Convolutional neu...
nmfeeds: [CV] https://t.co/3XoEoBypKR Quaternion Convolutional Neural Networks for Heterogeneous Image Processing. Convolutional ne...
arxivml: "Quaternion Convolutional Neural Networks for Heterogeneous Image Processing", Titouan Parcollet, Mohamed Morchid, … https://t.co/vVk41A38Wi
trinity_site: よう知らんが名前が強そう » [1811.02656] Quaternion Convolutional Neural Networks for Heterogeneous Image Processing https://t.co/MWJUgsJlWw
arxiv_cscv: Quaternion Convolutional Neural Networks for Heterogeneous Image Processing https://t.co/y6PYksnL5l
Images
Related