Robust higher order potentials for enforcing label consistency
This paper proposes a novel framework for labelling problems which is able to combine multiple segmentations in a principled manner. Our method is based on higher order conditional random fields and uses potentials defined on sets of pixels (image segments) generated using unsupervised segmentation...
主要な著者: | Kohli, P, Ladický, L, Torr, PHS |
---|---|
フォーマット: | Journal article |
言語: | English |
出版事項: |
Springer
2009
|
類似資料
-
Robust higher order potentials for enforcing label consistency
著者:: Kohli, P, 等
出版事項: (2008) -
Exact inference in multi-label CRFs with higher order cliques
著者:: Ramalingam, S, 等
出版事項: (2008) -
P3 and beyond: solving energies with higher order cliques
著者:: Kohli, P, 等
出版事項: (2007) -
Associative hierarchical CRFs for object class image segmentation
著者:: Ladický, L, 等
出版事項: (2009) -
Exact and approximate inference in associative hierarchical networks using graph cuts
著者:: Russell, C, 等
出版事項: (2010)