Distributed non-convex ADMM-based inference in large-scale random fields
We propose a parallel and distributed algorithm for solving discrete labeling problems in large scale random fields. Our approach is motivated by the following observations: i) very large scale image and video processing problems, such as labeling dozens of million pixels with thousands of labels, a...
Κύριοι συγγραφείς: | Miksik, O, Vineet, V, Pérez, P, Torr, PHS |
---|---|
Μορφή: | Conference item |
Γλώσσα: | English |
Έκδοση: |
British Machine Vision Association
2014
|
Παρόμοια τεκμήρια
-
Filter-based mean-field inference for random fields with higher-order terms and product label-spaces
ανά: Vineet, V, κ.ά.
Έκδοση: (2014) -
Filter-based mean-field inference for random fields with higher-order terms and product label-spaces
ανά: Vineet, V, κ.ά.
Έκδοση: (2012) -
Improved initialization and Gaussian mixture pairwise terms for dense random fields with mean-field inference
ανά: Vineet, V, κ.ά.
Έκδοση: (2012) -
Dynamic graph cuts for efficient inference in Markov random fields
ανά: Kohli, P, κ.ά.
Έκδοση: (2007) -
Smoothing ADMM for Sparse-Penalized Quantile Regression With Non-Convex Penalties
ανά: Reza Mirzaeifard, κ.ά.
Έκδοση: (2024-01-01)