Home > Research > Publications & Outputs > Context-guided diffusion for label propagation ...

Electronic data

  • ICCV2015

    Rights statement: ©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.

    Accepted author manuscript, 368 KB, PDF-document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Context-guided diffusion for label propagation on graphs

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Published
  • Kwang In Kim
  • James Tompkin
  • Hanspeter Pfister
  • Christian Theobalt
Close
Publication date7/12/2015
Host publication2015 IEEE International Conference on Computer Vision (ICCV)
PublisherIEEE
Pages2776-2784
Number of pages9
ISBN (Print)9781467383905
Original languageEnglish

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.

Bibliographic note

©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.