Group equivariant convolutional neural networks (G-CNNs) have been successfully applied in geometric deep learning. Typically, G-CNNs have the advantage over CNNs that they do not waste network capacity on training symmetries that should have been hard-coded in the network. The recently introduced framework of PDE-based G-CNNs (PDE-G-CNNs) generalises G-CNNs. PDE-G-CNNs have the core advantages that they simultaneously 1) reduce network complexity, 2) increase classification performance, and 3) provide geometric interpretability. Their implementations primarily consist of linear and morphological convolutions with kernels. In this paper we show that the previously suggested approximative morphological kernels do not always accurately approximate the exact kernels accurately. More specifically, depending on the spatial anisotropy of the Riemannian metric, we argue that one must resort to sub-Riemannian approximations. We solve this problem by providing a new approximative kernel that works regardless of the anisotropy. We provide new theorems with better error estimates of the approximative kernels, and prove that they all carry the same reflectional symmetries as the exact ones. We test the effectiveness of multiple approximative kernels within the PDE-G-CNN framework on two datasets, and observe an improvement with the new approximative kernels. We report that the PDE-G-CNNs again allow for a considerable reduction of network complexity while having comparable or better performance than G-CNNs and CNNs on the two datasets. Moreover, PDE-G-CNNs have the advantage of better geometric interpretability over G-CNNs, as the morphological kernels are related to association fields from neurogeometry.
翻译:以 G- CNN 为基础的 GDE- G- G- CNN 框架( PDE- G- G- CNN ) 最近推出的 GDE- G- CNN 框架一般G- CNN 。 PDE- G- CNN 的核心优势在于它们能够同时降低网络复杂性,2 提高分类性能,3 提供几何解释性。 GNN 与CN 相比的优势是,它们不会在网络内部将网络能力浪费在培训应使用硬码的对称上。最近推出的基于 PDE- G- GNNN( PDE- G- G- CNN) 的 GDE- G- GNN( PDE- G- G- CNN) 框架框架( G- G- GNNNNNN) 。 PDE- G- G- G- CNNNNN 的核心优势在于它们能够同时降低网络的对网络进行新的对立性能性变异性, 我们通过提供新的近近近的网络来解决这个问题。