TY  - CONF
AU  - Josep M. Gonfaus
AU  - Xavier Boix
AU  - Joost Van de Weijer
AU  - Andrew Bagdanov
AU  - Joan Serrat
AU  - Jordi Gonzalez
A2  - CVPR
PY  - 2010//
TI  - Harmony Potentials for Joint Classification and Segmentation
BT  - 23rd IEEE Conference on Computer Vision and Pattern Recognition
SP  - 3280–3287
N2  - 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.
SN  - 1063-6919
SN  - 978-1-4244-6984-0
UR  - 10.1109/CVPR.2010.5540048
UR  - http://dx.doi.org/10.1109/CVPR.2010.5540048
N1  - ADAS
ID  - Josep M. Gonfaus2010
ER  -