Lecture 6: Classification – Boosting and SVMs CAP 5415 Fall 2006.

Lecture 6: Classification – Boosting and SVMsCAP 5415

Fall 2006

Course Project

Basic Requirement: Implement a vision algorithm

How complex? The experiments/implementation details should be

interesting enough for a 4-5 page write-up. If you choose a relatively simple algorithm, then you

should do interesting experiments to test the algorithm's limits

Groups

I encourage you to work in groups Can do more interesting projects Should be more interesting projects

Come talk to me if you would like to work in a group, but don't know anyone

Group write-up: 6-8 pages Possible goal: CVPR07 Submission (Dec 4)

~20% acceptance rate, don't plan on submitting second-rate work

How do I pick a project?

Strategy #1: Pick topic that you think is interesting Read three papers on that topic Implement one Or implement your own solution Could be original research

Lots of opportunity in the area of computational photography

Come talk to me!!! I can point you to interesting papers that have come out

recently

Strategy #2

I have a few original research ideas Computational Photography Surveillance Object Segmentation

Come talk to me to see what you're interested in and if you need help finding partners for a group project

No advantage in terms of grading

Q:I work in one of the vision groups, can I just turn in my CVPR07

submission?

A: No

Well, actually

Your project may be related, but should not just be your current research project

Examples Related side project that you haven't had time to

pursue in depth Application of algorithms that you have developed

for one problem to a different problem Should have interesting experiments

Getting it done

Write-ups due Dec 2 Brief Proposal Due Nov 7th

I would prefer Oct 18th or 25th

Whatever you work on, keep me updated!!!! I am here to help!

Grading I will give you feedback on your proposal

The earlier you touch base with me, the better Once we agree, if you do what your proposal stated and

turn in a good-quality write-up, you will get an “A” What if it doesn't work?

It happens a lot! Good write-up explaining what went wrong, what you

think the underlying problems are and how you would fix them if you were to keep working on this project

I'm not talking about “I didn't understand the math” or “My code kept crashing”

Can still get an “A”

One last thing about projects

I will be scheduling project meetings to meet with each group at the end of November

Class will be canceled on November 21 That class will be your project meeting.

What's wrong with this decision boundary?

(Assume this is the training data)

What's wrong with this decision boundary?

What if you then tested on this data?

This decision boundary over-fit the training data Hard to do with a linear classifier, but easy with a

non-linear classifier

How to tell if your classifier is overfitting

Strategy #1:Hold out part of your data as a test set

What if data is hard to come by? Strategy #2: k-fold cross-validation

Break the data set into k parts For each part, hold a part out, then train the

classifier and use the held out part as a test set Slower than test-set method More efficient use of limited data

Basic Set-up for Boosting

We want to learn a classifier

We will assume that F(x) has the form

Basic Idea: Iteratively Choose weak learners and set the

weights

AdaBoost

Initialization:

D is a distribution over the training examples Can also be thought of as a weight on each

exampleFrom “A short introduction to boosting” by Freund and Schapire

Next Step: Get Weak Learner

The weak learner trained to do as well as possible on the weighted training set Must have better than 50% accuracy

From “A short introduction to boosting” by Freund and Schapire

Next Reset Weights


Demo

In this demo, each weak learner is a stump of the form (ax+by)>c

Looking at the algorithm again


Advantages A simple algorithm for learning robust classifiers

Freund & Shapire, 1995 Friedman, Hastie, Tibshhirani, 1998

Provides efficient algorithm for sparse visual feature selection Tieu & Viola, 2000 Viola & Jones, 2003

Easy to implement, does not require external optimization tools.

(From Tutorial on Object Detection by Torralba, Ferbus, and Li – ICCV 2005)

Where do the weak learners come from?

Any classifier can be a weak learner Common ones:

Stump: r(x) > c Decision tree (Another kind of classifier)

Combined with Adaboost, has been dubbed “Best off-the-shelf classifier” (Friedman, Hastie, and Tibshirani)

Application: Face Detection (Viola and Jones 2001)

Features

Threshold on the response to simple features(Figures copied from Robust Real-time Object Detection by Viola and Jones) (2001)

Why?

Viola and Jones introduce a trick that lets them compute the response to these features very quickly Called integral image

First step: Doing a running, cumulative sum across the image

Integral Image Can compute the response in a square very

easily

These features also capture important features of faces

How well does it work?

95% Detection Rate with a false positive rate of 1 in 14084

Is it fast?

In 2001, one 384x288 image every 0.7 seconds Not real-time How can we make it faster?

Use a cascade A classifier with 2 weak-learners detect 100% of

the faces with a 40% false positive rate Have eliminated 60% of the training set with very

little computation Can now train a slightly more complicated

classifier to eliminate even more examples

The implementation

32 layers Layer 1 – Two Weak Learners (Rejects 60% of

non-faces) Layer 2 – Five Weak Learners (Rejects 80% of

non-faces) Layers 3-5 – 20 Weak Learners Layers 6-7 – 50 Weak Learners Layers 8-12 – 100 Weak Learners Layers 13-32 – 200 Weak Learners

Computation On average 8 features out of 4297 possible features are evaluated at every

pixel

On a 700Mhz Pentium III, can process a 384x288 image in 0.067 seconds

Almost as accurate as without a cascade

The Support Vector Machine Boosted Classifiers and SVM's are probably the

two most popular classifiers today I won't get into the math behind SVM's, if you

are interested, you should take the pattern recognition course (highly recommended)

The Support Vector Machine

Last time, we considered the problem of linear classification

We used probabilities to fit the line


Consider a different criterion Called the margin


Margin – minimum distance from a data point to the decision boundary


The SVM finds the decision boundary that maximizes the margin


Data points along the boundary are known as support vectors

Non-Linear Classification in SVMs

Last time, I showed how you could do non-linear classification by using non-linear transformations of the features

x

y

This is the decision boundary fromx2 + 8xy + y2 > 0

This is the same as making a new set of features, then doing linear classification


The decision function can be expressed in terms of dot-products

Each α will be zero unless the vector is a support vector


What if we wanted to do non-linear classification?

We could transform the features and compute the dot product of the transformed features.

But there may be an easier way!

The Kernel Trick

Let Φ(x) be a function that transforms x into a different space

A kernel function K is a function such that

Example (Burges 98)

If

Then

This is called the polynomial kernel

Gaussian RBF Kernel

One of the most commonly used kernels

Equivalent to doing a dot-product in an infinite dimensional space

The Kernel Trick

So, with a kernel function K, the new classification rule is

Basic Ideas: Computing the kernel function should be easier

than computing a dot-product in the transformed space

Other algorithms, like logistic regression can also be “kernelized”

So what if I want to use an SVM?

There are well-developed packages with Python and MATLAB interfaces libSVM SVMLight SVMTorch

Lecture 6: Classification – Boosting and SVMs CAP 5415 Fall 2006.

Documents

Transcript of Lecture 6: Classification – Boosting and SVMs CAP 5415 Fall 2006.