TY  - JOUR
AU  - Xavier Boix
AU  - Josep M. Gonfaus
AU  - Joost Van de Weijer
AU  - Andrew Bagdanov
AU  - Joan Serrat
AU  - Jordi Gonzalez
PY  - 2012//
TI  - Harmony Potentials: Fusing Global and Local Scale for Semantic Image Segmentation
T2  - IJCV
JO  - International Journal of Computer Vision
SP  - 83
EP  - 102
VL  - 96
IS  - 1
N2  - 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 oversimplied model since multiple classes can be reasonably expected to appear within large regions. This simplied 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. Toaddress these issues, we propose a new consistency potential for image labeling problems, which we call the harmony potential. It can encode any possible combi-nation of labels, penalizing only unlikely combinations of classes. We also propose an eective 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.
SN  - 0920-5691
UR  - http://www.cat.uab.cat/Public/Publications/2012/BCV2012
L1  - http://refbase.cvc.uab.es/files/BGW2012.pdf
UR  - http://dx.doi.org/10.1007/s11263-011-0449-8
N1  - CAT;ISE;CIC;ADAS
ID  - Xavier Boix2012
ER  -