Context-guided diffusion for label propagation on graphs

Kwang In Kim, James Tompkin, Hanspeter Pfister, Christian Theobalt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

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.
Original languageEnglish
Title of host publicationProc. IEEE International Conference on Computer Vision (ICCV), 2015
PublisherIEEE
Pages2776-2784
Number of pages9
DOIs
Publication statusPublished - 2015
Event2015 IEEE International Conference on Computer Vision Workshop (ICCVW) - Santiago, Chile
Duration: 7 Dec 201513 Dec 2015

Conference

Conference2015 IEEE International Conference on Computer Vision Workshop (ICCVW)
CountryChile
CitySantiago
Period7/12/1513/12/15

Fingerprint Dive into the research topics of 'Context-guided diffusion for label propagation on graphs'. Together they form a unique fingerprint.

Cite this