RBF-GNN：用于基于伪坐标的图卷积的有理基函数
RBF-GNN: Rational Basis Functions for Pseudo-Coordinate based Graph Convolutions
浏览论文内容
中文总结 AI 辅助
提出RBF-GNN，用有理Padé基函数替代B样条，改进基于伪坐标的图卷积，在关键点匹配、形状匹配等任务上取得更优结果。
中文摘要 AI 辅助
我们提出了RBF-GNN，一种新的基于伪坐标的图神经网络架构，它考虑欧几里得、球面或角度坐标，并利用它们引入强大的空间归纳偏置。在架构上类似于SplineCNN，我们通过用有理Padé基函数替换效率较低、基于稀疏激活的B样条（其数量随维度呈指数增长）来改进后者。为了有效训练，我们提出了一种样条子空间初始化和方差保持的权重重新缩放。在实验上，我们在多种使用SplineCNN的流行神经网络架构上进行了评估。我们仅将SplineCNN替换为RBF-GNN。我们取得了改进的结果，包括在语义关键点匹配、形状匹配、基于事件的相机计算机视觉任务上。论文被接受后，我们将公开我们的实现。
英文摘要
We propose RBF-GNN, a new pseudo-coordinate based graph neural network architecture that takes into account Euclidean, spherical or angular coordinates and uses them to induce a powerful spatial inductive bias. Similar in architecture to SplineCNN, we improve upon the latter by replacing the less efficient sparse-activation based B-splines whose number grows exponentially with dimension by rational Padé basis functions. For effective training we propose a spline-subspace initialization and a variance-preserving weight rescaling. Experimentally, we evaluate on a number of popular neural network architectures that use SplineCNNs. We replace only the SplineCNNs with RBF-GNN. We achieve improved results, including on semantic keypoint matching, shape matching, event based camera computer vision tasks. Code is available at https://github.com/pawelswoboda/RationalBasisCNN.
发表机构
- Heinrich Heine University Düsseldorf（杜塞尔多夫海因里希·海涅大学）
机构由 AI 辅助整理，请以论文原文为准。
