mean-field theory and its applications in computer vision4 1

21
Mean-Field Theory and Its Applications In Computer Vision4 1

Upload: jaden-gonzales

Post on 28-Mar-2015

220 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Mean-Field Theory and Its Applications In Computer Vision4 1

Mean-Field Theory and Its Applications In Computer Vision4

1

Page 2: Mean-Field Theory and Its Applications In Computer Vision4 1

Motivation

2

Helps in incorporating region/segment consistency in the model

Pairwise CRF

Higher order CRF

Page 3: Mean-Field Theory and Its Applications In Computer Vision4 1

Motivation

3

Higher order terms can help in incorporating detectors into our model

Image

Without detector

With detector

Page 4: Mean-Field Theory and Its Applications In Computer Vision4 1

Marginal update

4

General form of meanfield update

Expectation of the cost given variable vi takes a label

Page 5: Mean-Field Theory and Its Applications In Computer Vision4 1

Marginal Update

5

General form of meanfield update

Expectation of the clique given variable vi takes a label

• Summation over the possible states of the clique

Page 6: Mean-Field Theory and Its Applications In Computer Vision4 1

Marginal Update in Meanfield

6

Some possible states

Total number of possible states: 36

labels

Page 7: Mean-Field Theory and Its Applications In Computer Vision4 1

Marginal Update in Meanfield

7

Exponential # of possible states for clique of size |c| and labels L: |L|C

Expectation evaluation (summation) becomes infeasible

Page 8: Mean-Field Theory and Its Applications In Computer Vision4 1

Marginal Update in Meanfield

8

• Use restricted form of cost

• Pattern based potential

Page 9: Mean-Field Theory and Its Applications In Computer Vision4 1

Marginal Update in Meanfield

9

Restrict the number of states to certain number of patterns

Simple patterns

Segment takes a label from label set of 4 patterns Or none

Page 10: Mean-Field Theory and Its Applications In Computer Vision4 1

Marginal Update in Meanfield

10

Expectation calculation is quite efficient

Page 11: Mean-Field Theory and Its Applications In Computer Vision4 1

Pattern based cost

11

Segment takes one of the forms

Page 12: Mean-Field Theory and Its Applications In Computer Vision4 1

Pattern based cost

12

Segment does not take one of the forms

Page 13: Mean-Field Theory and Its Applications In Computer Vision4 1

Pattern based cost

13

• Simple patterns

Simple patterns

• Pattern based higher order terms

Page 14: Mean-Field Theory and Its Applications In Computer Vision4 1

PN Potts based patterns

14

• PN Potts based patterns

Potts patterns

Page 15: Mean-Field Theory and Its Applications In Computer Vision4 1

Potts cost

15

• Potts cost

Potts patterns

Page 16: Mean-Field Theory and Its Applications In Computer Vision4 1

Marginal Update in Meanfield

16

General form of meanfield update

Expectation of the cost given variable vi takes a label

Page 17: Mean-Field Theory and Its Applications In Computer Vision4 1

Expectation update

17

Probability of segment taking that label

Potts patterns

Page 18: Mean-Field Theory and Its Applications In Computer Vision4 1

Expectation update

18

Probability of segment not taking that label

Potts patterns

Page 19: Mean-Field Theory and Its Applications In Computer Vision4 1

Expectation update

19

Expectation update

Potts patterns

Page 20: Mean-Field Theory and Its Applications In Computer Vision4 1

Complexity

20

• Expectation Updation:

• Time complexity• O(NL)

• Preserves the complexity of original filter based method

Page 21: Mean-Field Theory and Its Applications In Computer Vision4 1

PascalVOC-10 dataset

21

• Inclusion of PN potts term:

Algorithm Time (s) Overall Av. Recall Av. I/U

AHCRF+Cooc 36 81.43 38.01 30.09

Dense CRF 0.67 71.63 34.53 28.4

Dense + PN Potts

4.35 79.87 40.71 30.18

• Slight improvement in I/U score compared to more complex model which includes Pn Potts + cooccurrence terms• Almost 8-9 times faster than the alpha-expansion based method