arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.04893cs.LG
收藏

球面信号的卷积网络

Convolutional Networks for Spherical Signals

University of Amsterdam(阿姆斯特丹大学)

Taco Cohen, Mario Geiger, Jonas Köhler, Max Welling

摘要:

卷积网络在涉及平面信号(如图像)的学习问题中的成功是由于它们能够通过权重共享利用数据分布的平移对称性。许多科学和经济领域处理具有其他对称性的信号,例如球体上的旋转不变数据。例子包括气候和天气科学,天体物理学和化学。在本文中,我们提出了球形卷积网络。这些网络在球体和旋转组上使用卷积,这导致旋转权重共享和旋转等方差。使用合成球形MNIST数据集,我们表明球形卷积网络在处理旋转不变分类问题方面非常有效。

英文摘要:

The success of convolutional networks in learning problems involving planar signals such as images is due to their ability to exploit the translation symmetry of the data distribution through weight sharing. Many areas of science and egineering deal with signals with other symmetries, such as rotation invariant data on the sphere. Examples include climate and weather science, astrophysics, and chemistry. In this paper we present spherical convolutional networks. These networks use convolutions on the sphere and rotation group, which results in rotational weight sharing and rotation equivariance. Using a synthetic spherical MNIST dataset, we show that spherical convolutional networks are very effective at dealing with rotationally invariant classification problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑