SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels

We present Spline-based Convolutional Neural Networks (SplineCNNs), a variant of deep neural networks for irregular structured and geometric input, e.g., graphs or meshes. Our main contribution is a novel convolution operator based on B-splines, that makes the computation time independent from the kernel size due to the local support property of the B-spline basis functions... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Superpixel Image Classification 75 Superpixel MNIST SplineCNN Classification Error 4.78 # 4
Node Classification Citeseer SplineCNN Accuracy 79.20% # 3
Node Classification Cora SplineCNN Accuracy 89.48% # 2
Node Classification Pubmed SplineCNN Accuracy 88.88% # 3

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions