MRFs

1
(No Transcript)
2
MRFs
?(X1,X2)
3
2
1
X3
X1
X2
4
?(X2,X3,X3)
X4
3
CRFs
Image I
?(X1,X2,I)
3
2
1
X3
X1
X2
4
?(X2,X3,X3,I)
X4
4
Examples
X Image patches
Quattoni et al.
X Patches on a regular lattice
Kumar
5
Examples
X pixels, regions, image
He et al.
6
Issues

• Inference
• Easy only when the planets are aligned
• Approximate solutions only ? How good are they?
• Learning
• Difficult and slow
• Limits the complexity of the models

7
Issues

• Generality
• Can use arbitrary models but limited to
  restricted models in practice because of
  inference and learning challenges
• Global label inference
• Inference over global labeling of the data in
  theory, but limited propagation across image in
  practice
• Support limited by the complexity of learning and
  inference
• Use of complex graph and clique structure is
  difficult