Abstract

Hierarchical conditional random fields have been successfully applied to object segmentation. One reason is their ability to incorporate contextual information at different scales. However, these models do not allow multiple labels to be assigned to a single node. At higher scales in the image, this yields an oversimplified model, since multiple classes can be reasonable expected to appear within one region. This simplified model especially limits the impact that observations at larger scales may have on the CRF model. Neglecting the information at larger scales is undesirable since class-label estimates based on these scales are more reliable than at smaller, noisier scales. To address this problem, we propose a new potential, called harmony potential, which can encode any possible combination of class labels. We propose an effective sampling strategy that renders tractable the underlying optimization problem. Results show that our approach obtains state-of-the-art results on two challenging datasets: Pascal VOC 2009 and MSRC-21.

Keywords

Pascal (unit)ENCODESegmentationComputer scienceArtificial intelligenceConditional random fieldPattern recognition (psychology)Class (philosophy)Machine learning

Affiliated Institutions

Related Publications

Normalized cuts and image segmentation

We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach...

2000 IEEE Transactions on Pattern Analysis... 15440 citations

Publication Info

Year
2010
Type
article
Pages
3280-3287
Citations
156
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

156
OpenAlex

Cite This

Josep M. Gonfaus, Xavier Boix, Joost van de Weijer et al. (2010). Harmony potentials for joint classification and segmentation. , 3280-3287. https://doi.org/10.1109/cvpr.2010.5540048

Identifiers

DOI
10.1109/cvpr.2010.5540048