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...
Үндсэн зохиолчид: | Kohli, P, Ladický, L, Torr, PHS |
---|---|
Формат: | Journal article |
Хэл сонгох: | English |
Хэвлэсэн: |
Springer
2009
|
Ижил төстэй зүйлс
-
Robust higher order potentials for enforcing label consistency
-н: Kohli, P, зэрэг
Хэвлэсэн: (2008) -
Exact inference in multi-label CRFs with higher order cliques
-н: Ramalingam, S, зэрэг
Хэвлэсэн: (2008) -
P3 and beyond: solving energies with higher order cliques
-н: Kohli, P, зэрэг
Хэвлэсэн: (2007) -
Associative hierarchical CRFs for object class image segmentation
-н: Ladický, L, зэрэг
Хэвлэсэн: (2009) -
Exact and approximate inference in associative hierarchical networks using graph cuts
-н: Russell, C, зэрэг
Хэвлэсэн: (2010)