• German

Main Navigation

Fey/etal/2018a: SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels

Bibtype Inproceedings
Bibkey Fey/etal/2018a
Author Fey, Matthias and Lenssen, Jan Eric and Weichert, Frank and Müller, Heinrich
Title {SplineCNN}: Fast Geometric Deep Learning with Continuous {B}-Spline Kernels
Booktitle IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
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. As a main advantage, 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.
Year 2018
Projekt SFB876-B2,SFB876-A6
Url https://arxiv.org/abs/1711.08920
fey_etal_2018a.pdf [3957 KB]
Bibtex Here you can get this literature entry as BibTeX format.