Harmony potentials : Fusing global and local scale for semantic image segmentation

Xavier Boix, Josep M. Gonfaus, Joost Van De Weijer, Andrew D. Bagdanov, Joan Serrat, Jordi Gonzàlez

Research output: Contribution to journalArticleResearchpeer-review

77 Citations (Scopus)


The Hierarchical Conditional Random Field (HCRF) model have been successfully applied to a number of image labeling problems, including image segmentation. However, existing HCRF models of image segmentation do not allow multiple classes to be assigned to a single region, which limits their ability to incorporate contextual information across multiple scales. At higher scales in the image, this representation yields an oversimplified model since multiple classes can be reasonably expected to appear within large regions. This simplified model particularly limits the impact of information at higher scales. Since class-label information at these scales is usually more reliable than at lower, noisier scales, neglecting this information is undesirable. To address these issues, we propose a new consistency potential for image labeling problems, which we call the harmony potential. It can encode any possible combination of labels, penalizing only unlikely combinations of classes. We also propose an effective sampling strategy over this expanded label set that renders tractable the underlying optimization problem. Our approach obtains state-of-the-art results on two challenging, standard benchmark datasets for semantic image segmentation: PASCAL VOC 2010, and MSRC-21. © 2011 Springer Science+Business Media, LLC.
Original languageEnglish
Pages (from-to)83-102
JournalInternational Journal of Computer Vision
Publication statusPublished - 1 Jan 2012


  • Hierarchical conditional random fields
  • Semantic object segmentation


Dive into the research topics of 'Harmony potentials : Fusing global and local scale for semantic image segmentation'. Together they form a unique fingerprint.

Cite this