Deep Cyclic Group Networks
Lists
Only you see this
Abstract
We propose a new network architecture called deep cyclic group network (DCGN) that uses the cyclic group algebra for convolutional vector-neuron learning. The input to DCGN is a three-way tensor, where the mode-3 dimension corresponds to the dimensionality of the input data, e.g., three for RGB images. To handle vector-valued inputs, we replace scalar multiplication with circular convolution for the feedforward and backpropagation processes. As a result, every feature map and kernel map is a three-way tensor with the same mode-3 dimension as the input data. This way, DCGN may capture more of the relations among different data dimensions, especially for regression tasks where the target output has the same dimensionality as the input data. Moreover, DCGN can deal with input data of arbitrary dimensions, a property that existing architectures such as deep complex networks and deep quaternion networks (DQN) lack. Experiments show that DCGN indeed performs better than convolutional neural networks and DQN for two regression tasks, namely color image inpainting and multispectral image denoising.
BibTeX
@inproceedings{fan2019deep,
author = {Zhe-Cheng Fan and Tak-Shing Chan and Yi-Hsuan Yang and Jyh-Shing Roger Jang},
title = {{Deep Cyclic Group Networks}},
booktitle = {IJCNN},
year = {2019},
url = {https://openreview.net/forum?id=QV7F7i4sof},
}Loading related content...