Context-guided diffusion for label propagation on graphs

Kim, Kwang In and Tompkin, James and Pfister, Hanspeter and Theobalt, Christian (2015) Context-guided diffusion for label propagation on graphs. In: 2015 IEEE International Conference on Computer Vision (ICCV) :. IEEE, pp. 2776-2784. ISBN 9781467383905

[thumbnail of ICCV2015]
PDF (ICCV2015)
ICCV2015.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (377kB)


Existing approaches for diffusion on graphs, e.g., for label propagation, are mainly focused on isotropic diffusion, which is induced by the commonly-used graph Laplacian regularizer. Inspired by the success of diffusivity tensors for anisotropic diffusion in image processing, we presents anisotropic diffusion on graphs and the corresponding label propagation algorithm. We develop positive definite diffusivity operators on the vector bundles of Riemannian manifolds, and discretize them to diffusivity operators on graphs. This enables us to easily define new robust diffusivity operators which significantly improve semi-supervised learning performance over existing diffusion algorithms.

Item Type:
Contribution in Book/Report/Proceedings
Additional Information:
©2015 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
ID Code:
Deposited By:
Deposited On:
27 Oct 2015 15:28
Last Modified:
09 Apr 2024 00:49