1
Fast Primal-Dual Strategies for MRF Optimization
(Fast PD)
Robot Perception Lab
Taha Hamedani
Aug 2014
2
Overview
• A new efficient MRF optimization algorithm• generalizes α-expansion• at least 3-9 times faster than α-expansion• used for boosting the performance of dynamic MRFs, i.e. MRFs varying over time
• guarantee an almost optimal solution for a much wider class of NP-hard MRF problems
3
Energy Function
• weighted graph G (with nodes V , edges E and weights wpq), one seeks to assign a label xp (from a discrete set of labels L) to each p V , so that the ∈following cost is minimized:
• p(·), d(·, ·) determine the singleton and pairwise MRF potential functions
4
Primal-dual MRF optimization algorithms
• Theorem 1 (Primal-Dual schema). Keep generating pairs of integral-primal, dual solutions (xk, yk), until the elements of the last pair, (say x, y), are both feasible and have costs that are close enough, e.g. their ratio is ≤ f app:
• Then x is guaranteed to be an fapp-approximate solution to the optimal integral solution x , i.e. cTx ≤ f∗ app · cTx .∗
5
The primal dual schema
6
Fast primal-dual MRF optimization
• In the above formulation, θ ={ {θp}p V∈ , {θpq}pq E∈ } represents a vector of MRF-parameters that consists of all unary θp = {θp(·)} and pairwise θpq = {θpq(·, ·)}
• x ={{xp}p V∈ , {xpq}pq E∈ } denotes a vector of binary MRF-variables consisting of all unary subvectors xp = {xp(·)} and pairwise subvectors xpq = {xpq(·, ·)}. (0,1 variables)
• i.e, they satisfy xp(l) = 1 label l is assigned to p,⇔• while xpq(l, l ) = 1 labels l, l are assigned to p, q′ ⇔ ′
7
MRF constraints
• (first constraint) simply express the fact that a unique label must be assigned to each node p
• (second constraint) since they ensure that if xp(l) = xq(l ) = ′1, then xpq(l, l ) = 1 as well′
• (marginal polytope)
8
• local marginal polytope • connected with the linear programming (LP) relaxation, which is formed by replacing the integer constraints xp(·), xpq(·, ·) {0, 1} with ∈the relaxed constraints
• xp(·), xpq(·, ·) ≥ 0
9
• The original (possibly difficult) optimization problem decomposes into easier sub problems (called the slaves) that are coordinated by a master problem via message exchanging
10
• decompose the original MRF optimization problem, which is NP-hard (since it is defined on a general graph G )
• decompose into a set of easier MRF sub problems, each one defined on a tree T G . ⊂
• Needed to transform our problem into a more appropriate form by introducing a set of auxiliary variables.
• let T (G ) be a set of sub trees of graph G (cover at least one node and edge of graph G)
11
• For each tree T T (G ) we will then ∈imagine that there is a smaller MRF defined just on the nodes and edges of tree T
• We will associate to it a vector of MRF-parameters θT.
• as well as a vector of MRF-variables xT (these have similar form to vectors θ and x of the original MRF, except that they are smaller in size) (Decomposition)
12
Redundancy
• MRF-variables contained in vector xT will be redundant
• initially assume that they are all equal to the corresponding MRF-variables in vector x, i.e it will hold xT= x|T
• x|T represents the sub vector of x containing MRF-variables only for nodes and edges of tree T
13
• all the vectors {θT} will be defined so that they satisfy the following conditions:
• Here, T (p) and T (pq) denote the set of all trees of T (G ) that contain node p and edge pq respectively.
14
Energy Decomposition
• The first constraints can reduced by :
• MRF problem can decomposed as :
15
• It is clear that without constraints xT= x|T , this problem would decouple into a series of smaller MRF problems (one per tree T )
• Lagrangian dual form :
• Eliminate vector x by minimizing over it :
16
• The resulting lagrangian dual form is simplified as :
• Dual from by maximizing over feasible set :
• Master• Slave
17
According to Lemma 1 :• λT must first be updated as
• Sub gradient of gt is equal to optimal solution of slave problem :
18
Fast PD procedure
19
References• [1] Komodakis, N.; Paragios, N.; Tziritas, G., "MRF Energy Minimization and
Beyond via Dual Decomposition," Pattern Analysis and Machine Intelligence, IEEE Transactions on , vol.33, no.3, pp.531,552, March 2011.
• [2] Chaohui Wang, Nikos Komodakis, Nikos Paragios, Markov Random Field modeling, inference & learning in computer vision & image understanding: A survey, Computer Vision and Image Understanding, Volume 117, Issue 11, November 2013, Pages 1610-1627, ISSN 1077-3142.
Thank You
?
Top Related