Computer vision: models,

learning and inference

Chapter 10
Graphical Models
 Independence
• Two variables x1 and x2 are independent if their joint
probability distribution factorizes as
Pr(x1, x2)=Pr(x1) Pr(x2)

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 2
 Conditional independence
• The variable x1 is said to be conditionally
independent of x3 given x2 when x1 and x3 are
independent for fixed x2.

• When this is true the joint density factorizes in a

certain way and is hence redundant.

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 3
 Conditional independence

• Consider joint pdf of three discrete variables x1, x2, x3

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 4
 Conditional independence

• Consider joint pdf of three discrete variables x1, x2, x3

• The three marginal distributions show that no pair of variables is independent

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 5
 Conditional independence

• Consider joint pdf of three discrete variables x1, x2, x3

• The three marginal distributions show that no pair of variables is independent
• But x1 is independent of x2 given x3

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 6
 Graphical models
• A graphical model is a graph based
representation that makes both factorization
and conditional independence relations easy
to establish

• Two important types:

– Directed graphical model or Bayesian network
– Undirected graphical model or Markov network

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 7
 Directed graphical models
• Directed graphical model represents probability
distribution that factorizes as a product of
conditional probability distributions

where pa[n] denotes the parents of node n

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 8
 Directed graphical models
• To visualize graphical model from factorization
– add one node per random variable and draw arrow to each
variable from each of its parents.

• To extract factorization from graphical model

– Add one term per node in the graph Pr(xn| xpa[n])
– If no parents then just add Pr(xn)

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 9
 Example 1

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 10
 Example 1

= Markov Blanket of variable x8 – Parents, children

and parents of children
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 11
 Example 1

If there is no route between two variables and

they share no ancestors, they are independent.
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 12
 Example 1

A variable is conditionally independent of all others,

given its Markov Blanket
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 13
 Example 1

General rule:

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 14
 Example 2

The joint pdf of this graphical model factorizes as:

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 15
 Example 2

The joint pdf of this graphical model factorizes as:

It describes the original example:

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 16
 Example 2

Here the arrows meet head to tail at x2, and so x1 is

conditionally independent of x3 given x2.

General rule:

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 17
 Example 2

Algebraic proof:

No dependence on x3 implies that x1 is conditionally

independent of x3 given x2.
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 18
 Redundancy
Conditional independence can be
thought of as redundancy in the full
distribution

4 + 3x4 + 2x3
= 22 entries
4 x 3 x 2 = 24 entries

Redundancy here only very small, but with larger models

can be very significant.
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 19
 Example 3

Mixture of t-distribution Factor analyzer

Gaussians
Blue boxes = Plates. Interpretation: repeat contents of box
number of times in bottom right corner.
Bullet = variables which are not treated as uncertain
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 20
 Undirected graphical models
Probability distribution factorizes as:

Partition Product over C Potential function

function functions (returns non-
(normalization negative number)
constant)
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 21
 Undirected graphical models
Probability distribution factorizes as:

Partition
function
(normalization For large systems, intractable to compute
constant)
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 22
 Alternative form

Can be written as Gibbs Distribution:

where Cost function

(positive or negative)
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 23
 Cliques
Better to write undirected model as

Product over Clique

cliques Subset of variables

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 24
 Undirected graphical models
• To visualize graphical model from factorization
– Sketch one node per random variable
– For every clique, sketch connection from every node to
every other

• To extract factorization from graphical model

– Add one term to factorization per maximal clique (fully
connected subset of nodes where it is not possible to add
another node and remain fully connected)

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 25
 Conditional independence
• Much simpler than for directed models:

One set of nodes is conditionally independent of another

given a third if the third set separates them (i.e.
Blocks any path from the first node to the second)

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 26
 Example 1

Represents factorization:

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 27
 Example 1

By inspection of graphical model:

x1 is conditionally independent of x3 given x2, as the

route from x1 to x3 is blocked by x2.

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 28
 Example 1

Algebraically:

No dependence on x3 implies that x1 is conditionally

independent of x3 given x2.
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 29
 Example 2

• Variables x1 and x2 form a clique (both connected to

each other)
• But not a maximal clique, as we can add x3 and it is
connected to both
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 30
 Example 2

Graphical model implies factorization:

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 31
 Example 2

Or could be....

... but this is less general

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 32
Comparing directed and undirected models

Executive summary:

• Some conditional independence patterns can be

represented as both directed and undirected
• Some can be represented only by directed
• Some can be represented only by undirected
• Some can be represented by neither

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 33
 Comparing directed and undirected models

These models represent same independence / There is no undirected model that

conditional independence relations can describe these relations

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 34
Comparing directed and undirected models

There is no directed model that Closest example,

can describe these relations but not the same
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 35
 Graphical models in computer vision

Chain model Interpreting sign

(hidden Markov model) language sequences

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 36
 Graphical models in computer vision

Tree model Parsing the human body

Note direction of links, indicating that we’re building
a probability distribution over the data, i.e.
generative models:
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 37
 Graphical models in computer vision

Grid model Semantic

Markov random field segmentation
(blue nodes)
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 38
Graphical models in computer vision

Chain model Tracking contours

Kalman filter

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 39
Inference in models with many unknowns

• Ideally we would compute full posterior

distribution Pr(w1...N|x1...N).
• But for most models this is a very large discrete
distribution – intractable to compute
• Other solutions:
– Find MAP solution
– Find marginal posterior distributions
– Maximum marginals
– Sampling posterior
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 40
 Finding MAP solution

• Still difficult to compute – must search

through very large number of states to find
the best one.

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 41
 Marginal posterior distributions

• Compute one distribution for each variable wn.

• Obviously cannot be computed by computing full
distribution and explicitly marginalizing.
• Must use algorithms that exploit conditional
independence!
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 42
 Maximum marginals

• Maximum of marginal posterior distribution for

each variable wn.
• May have probability zero; the states can be
individually probable, but never co-occur.

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 43
 Maximum marginals

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 44
 Sampling the posterior

• Draw samples from posterior Pr(w1...N|x1...N).

– use samples as representation of distribution
– select sample with highest prob. as point sample
– compute empirical max-marginals
• Look at marginal statistics of samples

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 45
 Drawing samples - directed

To sample from directed model, use ancestral sampling

• work through graphical model, sampling one variable at

a time.
• Always sample parents before sampling variable
• Condition on previously sampled values

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 46
Ancestral sampling example

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 47
 Ancestral sampling example

To generate one sample:

1. Sample x1* from Pr(x1) 4. Sample x3* from Pr(x3| x2*,x4*)
2. Sample x2* from Pr(x2| x1*) 5. Sample x5* from Pr(x5| x3*)
3. Sample x4* from Pr(x4| x1*, x2*)
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 48
 Drawing samples - undirected
• Can’t use ancestral sampling as no sense of
parents / children and don’t have conditional
probability distributions
• Instead us Markov chain Monte Carlo method
– Generate series of samples (chain)
– Each depends on previous sample (Markov)
– Generation stochastic (Monte Carlo)
• Example MCMC method = Gibbs sampling

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 49
 Gibbs sampling
To generate new sample x in the chain
– Sample each dimension in any order
– To update nth dimension xn
• Fix other N-1 dimensions
• Draw from conditional distribution Pr(xn| x1...N\n)
Get samples by selecting from chain
– Needs burn-in period
– Choose samples spaced apart, so not correlated

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 50
Gibbs sampling example: bi-variate normal
distribution

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 51
Gibbs sampling example: bi-variate normal
distribution

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 52
 Learning in directed models

Use standard ML formulation

where xi,n is the nth dimension of the ith training example.

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 53
Learning in undirected models
Write in form of Gibbs distribution

Maximum likelihood formulation

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 54
 Learning in undirected models

PROBLEM: To compute first term, we must sum over all

possible states. This is intractable

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 55
 Contrastive divergence
Some algebraic manipulation

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 56
 Contrastive divergence
Now approximate:

Where xj* is one of J samples from the distribution.

Can be computed using Gibbs sampling. In practice, it is
possible to run MCMC for just 1 iteration and still OK.
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 57
Contrastive divergence

Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 58
 Conclusions
Can characterize joint distributions as
– Graphical models
– Sets of conditional independence relations
– Factorizations
Two types of graphical model, represent different
but overlapping subsets of possible
conditional independence relations
– Directed (learning easy, sampling easy)
– Undirected (learning hard, sampling hard)
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 59