ICCV 2015
 
Context-guided diffusion for label propagation on graphs

Kwang In Kim James Tompkin Hanspeter Pfister Christian Theobalt
Lancaster University MPI für Informatik Harvard University SEAS

Abstract
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.

 
@inproceedings{KTPT2015:ICCV,
author = {Kwang In Kim and James Tompkin and Hanspeter Pfister and Christian Theobalt},
title = {Context-guided diffusion for label propagation on graphs},
booktitle = {Proc. ICCV},
pages = {2776--2784},
year = {2015},
}
   
Paper
PDF (0.4 MB)
  Supplemental Material
PDF (0.2 MB)

Resources
  • Code coming soon
Acknowledgements
Kwang In Kim thanks EPSRC EP/M00533X/1. James Tompkin and Hanspeter Pfister thank NSF CGV-1110955, the Air Force Research Laboratory, and the DARPA Memex program. Christian Theobalt thanks the Intel Visual Computing Institute.