Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich

Menu
Home Teaching Summer Semester 2019 Probabilistic Graphical Models in Computer Vision (IN2329) (2h + 2h, 5 ECTS)

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
teaching:ss2019:pgm2019 [2019/06/04 14:49]
Zhenzhang Ye
teaching:ss2019:pgm2019 [2019/07/30 15:28] (current)
Zhenzhang Ye
Line 1: Line 1:
 ====== Probabilistic Graphical Models in Computer Vision (IN2329) (2h + 2h, 5 ECTS) ====== ====== Probabilistic Graphical Models in Computer Vision (IN2329) (2h + 2h, 5 ECTS) ======
 <​html>​ <​html>​
-<b> Announcement:​ <br />  <br /> +<b> Announcement:​ </b><br /> </html> 
-There will be NO tutorial on Wednesday, 12.06.2019. Sheet5 should be submitted on 17.06.<br />  ​ +The schedule of repeat exam is announced. See below for details.\\ 
-There will be NO lecture on Wednesday, 24.04.2019. +There was an error in the exercise sheet 9, which is corrected now (2019.07.09 16:00). \\ 
-</​b>​ +The last lecture on 22.07 will be on deep Boltzmann machines presented by [[:​members:​sheny|Yuesong Shen]]. \\ 
-</​html> ​\\+There will be NO tutorial on Wednesday, 12.06.2019. Sheet5 should be submitted on 17.06. ​\\ 
 +There will be NO lecture on Wednesday, 24.04.2019.\\
  
 \\ \\
Line 12: Line 13:
 </b> </b>
 </​html>​ \\ </​html>​ \\
-Several problems in computer vision can be cast as a labeling problem. Typically, such problems arise from Markov Random Field (MRFmodels, which provide an elegant framework of formulating various types of labeling problems in imaging+Several problems in computer vision can be cast as a labeling problem. Typically, such problems arise from Markov Random Field (undirected graphical models), which provide an elegant framework of formulating various types of labeling problems in vision
-By making use of certain assumptions some nice“ MRF models can be solved in polynomial time, whereas ​others ​are NP hard. We will see bothefficient algorithms for solving the nice“ problems and relaxation strategies for the hard“ ones.\\+Under certain assumptions some "nice" ​MRF models can be solved in polynomial time, whereas ​other approaches ​are NP hard. We will see both efficient algorithms for solving the "nice" ​problems and relaxation strategies for the "hard" ​ones.\\
  
 {{ :​teaching:​ss2019:​pgm2019:​graph_model_1.png?​500 |}}\\ {{ :​teaching:​ss2019:​pgm2019:​graph_model_1.png?​500 |}}\\
Line 37: Line 38:
 - Approximative inference techniques: - Approximative inference techniques:
   * Loopy belief propagation   * Loopy belief propagation
-  * Mean field, variational inference+  * Mean field, ​principle of variational inference
   * Sampling methods   * Sampling methods
  
Line 84: Line 85:
 Date: August 05th, 08:30 - 09:45. \\ Date: August 05th, 08:30 - 09:45. \\
 Place: 102, Interims Hörsaal 2 (5620.01.102) \\ Place: 102, Interims Hörsaal 2 (5620.01.102) \\
-The final exam will be written. ​+The final exam will be written. No cheat sheet is allowed. 
 + 
 +== Repeat Exam == 
 +Date: October 08th, 10:30 - 11:45.\\ 
 +Place: 102, Interims Hörsaal 2 (5620.01.102) \\ 
 +The repeat exam will be written. No cheat sheet is allowed.
  
 == Lecture Materials == == Lecture Materials ==
 Course material (slides and exercise sheets) can be accessed [[teaching:​ss2019:​pgm2019:​materials|here]]. \\ \\ Send an email to [[pgm-ss19@vision.in.tum.de]] if you need the password. Course material (slides and exercise sheets) can be accessed [[teaching:​ss2019:​pgm2019:​materials|here]]. \\ \\ Send an email to [[pgm-ss19@vision.in.tum.de]] if you need the password.

Rechte Seite

Informatik IX
Chair of Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching

info@vision.in.tum.de