COMP 875 Machine Learning Methods in Image Analysis

Содержание

Слайд 2

What the class is about

“Applied” machine learning and statistical methods
Applications are primarily,

What the class is about “Applied” machine learning and statistical methods Applications
though not exclusively, to computer vision and medical imaging
Students from other research areas are welcome
Exact list of topics to be determined by you!

Слайд 3

Who should take this class?

This is meant as an “advanced” graduate course
Ideally,

Who should take this class? This is meant as an “advanced” graduate
you should have taken COMP 665, 775, 776, or Data Mining (or similar courses elsewhere)
You should be comfortable reading and understanding papers in recent conferences such as CVPR, ICCV, MICCAI, NIPS, ICML, etc.
You should have some experience doing research presentations
If you have questions or doubts about your background, please talk to me after this class

Слайд 4

Why Machine Learning?

Image analysis early on: simple tasks, few images

L. G. Roberts,

Why Machine Learning? Image analysis early on: simple tasks, few images L.
Machine Perception of Three Dimensional Solids, Ph.D. thesis, MIT Department of Electrical Engineering, 1963.

Слайд 5

Why Machine Learning?

Image analysis early on: try to program a computer directly

Why Machine Learning? Image analysis early on: try to program a computer
using rules and symbolic representations

Y. Ohta, T. Kanade, and T. Sakai, “An Analysis System for Scenes Containing objects with Substructures,” Proceedings of the Fourth International Joint Conference on Pattern Recognition, 1978, pp. 752-754.

Слайд 6

Today: Lots of data, complex tasks

Why Machine Learning?

Today: Lots of data, complex tasks Why Machine Learning?

Слайд 7

Today: Lots of data, complex tasks
Instead of trying to encode rules directly,

Today: Lots of data, complex tasks Instead of trying to encode rules
learn them from examples of inputs and desired outputs

Why Machine Learning?

Слайд 8

Not Just Image Analysis

Speech recognition
Document analysis
Spam filtering
Computer security
Statistical debugging
Bioinformatics
….

Not Just Image Analysis Speech recognition Document analysis Spam filtering Computer security Statistical debugging Bioinformatics ….

Слайд 9

Topics (tentative)

Classifiers: linear models, boosting, support vector machines
Kernel methods
Bayesian methods, Expectation

Topics (tentative) Classifiers: linear models, boosting, support vector machines Kernel methods Bayesian
Maximization
Random field models
Sampling techniques such as Markov Chain Monte Carlo
Unsupervised learning: density estimation, clustering
Manifold learning and dimensionality reduction
Distance metric learning
Semi-supervised learning
Online and active learning
Sequential inference (i.e., tracking)
Large-scale learning

Слайд 10

Class requirements

Class format: lectures and student presentations
Grading:
Presentation: 35%
Project: 35%
Participation: 30%

Class requirements Class format: lectures and student presentations Grading: Presentation: 35% Project: 35% Participation: 30%

Слайд 11

Presentation

You are “professor for a day”: you need to give a one-hour

Presentation You are “professor for a day”: you need to give a
lecture that would be interesting and accessible to all the students in the class
You are responsible for selecting your own topic and paper(s)
Look at the list of reading materials on the class webpage
Look through recent conference proceedings
Pick a topic of interest based on your own research

Слайд 12

Presentation Guidelines

Evaluation criteria
Integration: utilize multiple sources
Critical thinking: separate the essential from the

Presentation Guidelines Evaluation criteria Integration: utilize multiple sources Critical thinking: separate the
non-essential; critique the papers you present; think of alternative applications and future research directions
Interactivity: try to involve the rest of the class
Structuring the presentation
Will depend on your focus
Broadly speaking, you may want to focus either on a particular learning topic, or a particular application

Слайд 13

Sample Presentation Outline

Introduction
Problem definition
Problem formulation
Significance
Survey of methods for solving this problem
Detailed

Sample Presentation Outline Introduction Problem definition Problem formulation Significance Survey of methods
presentation of one or more specific methods
Discussion
Pluses and minuses of different methods
Compare and contrast different approaches
Ideas for improvement and future research
Alternative applications
Alternative methods for solving the same problem
Connect your topic to other topics discussed earlier in class

Слайд 14

Presentation Timeline

Reading list: due next Thursday, September 3rd
Preliminary slides: due Monday

Presentation Timeline Reading list: due next Thursday, September 3rd Preliminary slides: due
the week before your scheduled presentation
Practice meeting: scheduled for the week before your presentation
Final slides: due by the end of the day after your presentation
All of the above are part of your presentation grade (35% of total class grade)
A note on slides: you must explicitly credit all sources

Слайд 15

Project

Your project topic may be the same as your presentation topic
Not required,

Project Your project topic may be the same as your presentation topic
but may make your life easier
Two options: implementation or survey paper

Слайд 16

Implementation

Implement one or more methods from literature
Conduct a comparative evaluation
Implement your own

Implementation Implement one or more methods from literature Conduct a comparative evaluation
ideas or extensions of existing methods
Deliverable: an “informal” final report and (possibly) a short presentation
Students may collaborate, but each must submit his/her deliverables
You can use existing code and/or software, provided you document all your sources and it doesn’t make your project trivial

Слайд 17

Survey Paper

Comprehensive tutorial, literature review
A “formal” academic paper
Typeset in LaTeX, 10-15 pages

Survey Paper Comprehensive tutorial, literature review A “formal” academic paper Typeset in
(single-spaced, 11pt font)
Must be individual

Слайд 18

Project timeline (tentative)

Project proposal: due end of September (details to follow)
Progress report

Project timeline (tentative) Project proposal: due end of September (details to follow)
(for implementation) or draft paper (for survey, ~5 pages): due end of October
Final report or paper: due last day of class (December 8th)
All of the above are part of your project grade (35% of total class grade)

Слайд 19

Participation (30% of the grade)

Class attendance, being on time
Answer questions in review

Participation (30% of the grade) Class attendance, being on time Answer questions
sessions at the beginning of class
Be prepared
Read all the material before the class and come up with ~3 questions for discussion
I may call on anyone at any time
Participate in discussions
Send email to me and/or the class mailing group links to material that may be of interest
If you never speak up in class, the best grade you can get is P+!
Имя файла: COMP-875-Machine-Learning-Methods-in-Image-Analysis.pptx
Количество просмотров: 168
Количество скачиваний: 0