Quaternion Product Units for Deep Learning on 3D Rotation Groups.
Computer Vision and Pattern Recognition(2019)
摘要
We propose a novel quaternion product unit (QPU) to represent data on 3D rotation groups. The QPU leverages quaternion algebra and the law of 3D rotation group, representing 3D rotation data as quaternions and merging them via a weighted chain of Hamilton products. We prove that the representations derived by the proposed QPU can be disentangled into "rotation-invariant" features and "rotation-equivariant" features, respectively, which supports the rationality and the efficiency of the QPU in theory. We design quaternion neural networks based on our QPUs and make our models compatible with existing deep learning models. Experiments on both synthetic and real-world data show that the proposed QPU is beneficial for the learning tasks requiring rotation robustness.
更多查看译文
关键词
3D rotation data,Hamilton products,rotation-invariant features,rotation robustness,quaternion product unit,3D rotation group,QPU leverages quaternion algebra,deep learning,quaternion neural network design
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要