SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
Authors:
- Matthias FeyMFMatthias Fey
- Jan Eric LenssenJLJan Eric Lenssen
- Frank WeichertFWFrank Weichert
- Heinrich MullerHMHeinrich Muller
- 1 June 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 869-877
Abstract
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. As a result, we obtain a generalization of the traditional CNN convolution operator by using continuous kernel functions parametrized by a fixed number of trainable weights. In contrast to related approaches that filter in the spectral domain, the proposed method aggregates features purely in the spatial domain. In addition, SplineCNN allows entire end-to-end training of deep architectures, using only the geometric structure as input, instead of handcrafted feature descriptors. For validation, we apply our method on tasks from the fields of image graph classification, shape correspondence and graph node classification, and show that it outperforms or pars state-of-the-art approaches while being significantly faster and having favorable properties like domain-independence. Our source code is available on GitHub1.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Geometric Deep Learning: Going beyond Euclidean dataIEEE Signal Processing Magazine, 2017
- SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation2017
- Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs2017
- Geodesic Convolutional Neural Networks on Riemannian Manifolds2015
- FAUST: Dataset and Evaluation for 3D Mesh Registration2014
- Blended intrinsic mapsACM Transactions on Graphics, 2011
- Collective Classification in Network DataAI Magazine, 2008
- Weighted Graph Cuts without Eigenvectors A Multilevel ApproachIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- The NURBS Book1997