Revertible deep convolutional networks with iterated directional filter bank
Can Xu, Hongkai Xiong · 2016
Efficient image representation methods are of great significance in image processing. This paper proposes an invertible deep convolutional network where the entire architecture is constructed by a decomposition process and a frequency recombination process. The decomposition allows frequency division in both the lower and higher part at the same time on each layer. It is implemented by using iterated directional filter banks. Perfect reconstruction is available if we adopt biorthogonal qincunx filter banks. The remaining frequency recombination process is adjoined to the architecture to transform the uniform frequency partition to nonuniform one and thereby increase the efficiency and flexibility. Numerical experiments reveal that the underlying network has good performance especially for images with large amount of fine-grained information.