论文标题
DeepSphere：基于图的球形CNN
DeepSphere: a graph-based spherical CNN
论文作者
论文摘要
为球形神经网络设计卷积需要在效率和旋转模棱两可之间进行微妙的权衡。 DeepSphere是一种基于采样球体的图表表示的方法，在这两个desiderata之间达到了可控制的平衡。这个贡献是双重的。首先，我们从理论和经验上研究了对基础图的影响如何相对于顶点和邻居的数量的影响。其次，我们评估了有关相关问题的深度。实验显示出最新的性能，并证明了该配方的效率和灵活性。也许令人惊讶的是，与以前的工作进行比较表明，各向异性过滤器可能是不必要的代价。我们的代码可在https://github.com/deepsphere上找到
Designing a convolution for a spherical neural network requires a delicate tradeoff between efficiency and rotation equivariance. DeepSphere, a method based on a graph representation of the sampled sphere, strikes a controllable balance between these two desiderata. This contribution is twofold. First, we study both theoretically and empirically how equivariance is affected by the underlying graph with respect to the number of vertices and neighbors. Second, we evaluate DeepSphere on relevant problems. Experiments show state-of-the-art performance and demonstrates the efficiency and flexibility of this formulation. Perhaps surprisingly, comparison with previous work suggests that anisotropic filters might be an unnecessary price to pay. Our code is available at https://github.com/deepsphere
