Stat 238

Vision as Bayesian Inference

Mon/Wed: 12:00-1:20 Winter 2010, Franz 2258A.
 
www.stat.ucla.edu/~yuille/Courses/UCLA/Stat_238/Stat_238.html.
 

Course Description

This course models vision as Bayesian Inference. It concentrates on visual tasks such as segmenting images, detecting objects in images, and recognizing objects. Its goal is to describe the state of the art techniques. The handouts consist of copies of the lecture notes and related papers.

Reading Material

Grading Plan: 3  homework assignments (20% each). Term project (40%).

Tentative Schedule.

Lecture

Date

Topics

Reading Materials

Handwritten  Notes

Handouts

1

01-06

Introduction to the Course:
Statistical Edge Detection

statistical_regions.pdf

Lecture1.pdf

  chp1.pdf

2

01-08

Probability Distributions on Graphs:
Basic Introduction
        GYtics.pdf
Lecture2.pdf
  chp2.pdf

3

01-13

MRF models :
With and without hidden variables.
       segmentation_overview.pdf
Lecture3.pdf
   chp5.pdf

4

01-15

            Free Energies, EM and Mean Field Theory.
         Steepest Descent, Discrete Iterative Algorithms
     YuilleMicroBook.pdf
Lecture4.pdf

  

5

01-20

Belief Propagation:
Dynamic Programming

 

Lecture5.pdf
      chp9.pdf
     6
01-22
MCMC:
Brief description of MCMC

Lecture6.pdf
chp4.pdf
     7
01-27
Hidden Markov Models and SCFG's:
Learning and Inference by Dynamic Programming
   chang_peng_2002_2.pdf
Lecture7.pdf
Lecture7.5.pdf
  chp6.pdf
     8
02-01
Maximum Likelihood and Discriminative Learning:
Without hidden variables. ML versus AdaBoost

Lecture8.pdf
 chp3.pdf

9

02-03

Maximum Likelihood and Discriminative Learning:
With hidden variables. Structure ML.
   yu_joachims_09a.pdf
Lecture9.pdf
    tsochantaridis_etal_04a.pdf

10

02-08

Graphical Models of Objects
Introduction + more structural learning.

              

  NIPS2003_AA04.pdf
 Lecture10.pdf
  hand_cviu00J.pdf
  fergus03object.pdf

11

02-10

                 Hierarchical Object Models

 


   Lecture11.pdf

12

02-17

 
                  Hierarchical Models (Cont).
 


 HLLM08pami_Alan.pdf


Lecture12.pdf

notes10.pdf

notes11.pdf

13

02-22

                  Hierarchical Models (Learning).
  RCM_sum.pdf
 TPAMI-2007-03-0146-2.pdf
Lecture13.pdf
notes12.pdf

14

02-2

Deep Belief Networks
Active Appearance Models
  deepbelief.pdf
Lecture14.pdf


15

03-01

Active Basis Mode
  http://www.stat.ucla.edu/~ywu/AB/ActiveBasisMarkII.html
ywu.pdf

 

16

03-03

Lighting Models

Lecture16.pdf
                        chp11.pdf

17

03-08

Jury Duty   

 



18

03-10

Geometry of Vision: I
  SzeliskiBook_20100227_draft.pdf
 Lecture17.pdf


19

03-10

 
Geometry of Vision: II

 


 

   

 

 

 


 

 

 

Final Project Due 20/March. Hand in to Prof. Yuile. Office or Mailbox