Quaternion Convolutional Neural Networks

By Xuanyu Zhu, Yi Xu, Hongteng Xu, Changjian Chen. 2018

195 citations recorded by the source corpus.

Neural networks in the real domain have been studied for a long time and achieved promising results in many vision tasks for recent years. However, the extensions of the neural network models in other number fields and their potential applications are not fully-investigated yet. Focusing on color images, which can be naturally represented as quaternion matrices, we propose a quaternion convolutional neural network (QCNN) model to obtain more representative features. In particular, we re-design the basic modules like convolution layer and fully-connected layer in the quaternion domain, which can be used to establish fully-quaternion convolutional neural networks. Moreover, these modules are compatible with almost all deep learning techniques and can be plugged into traditional CNNs easily. We test our QCNN models in both color image classification and denoising tasks. Experimental results show that they outperform the real-valued CNNs with same structures.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Anh Tuan Luu
2. Siu Cheung Hui
3. Yi Tay
4. Shuai Zhang
5. Aston Zhang
6. Jie Fu
7. Alvin Chan
8. Shuohang Wang

Citations in the corpus

• Compacter: Efficient Low-Rank Hypercomplex Adapter Layers (2021, background): “Hypercomplex representations Deep learning advances in the hypercomplex domain are in a nascent stage, and most work is fairly recent [40, 41, 42, 43, 44].”
• Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks (2019, methodology): “In parallel Zhu et al. proposed Quaternion CNNs and applied them to image classification and de-noising tasks (Zhu et al., 2018).”
• Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameters (2021, methodology): “Though parameter reusing by component-wise partitioning in Quaternion space has demonstrated success (Parcollet et al., 2018b; Zhu et al., 2018; Parcollet et al., 2019; Tay et al., 2019), one key problem is that hypercomplex space only exists at very few predefined dimensionalities, such as 4D…”