Loading in 5 sec....

Learning and Vision: Discriminative ModelsPowerPoint Presentation

Learning and Vision: Discriminative Models

- 177 Views
- Updated On :

Learning and Vision: Discriminative Models. Chris Bishop and Paul Viola. Part II: Algorithms and Applications. Part I: Fundamentals Part II: Algorithms and Applications Support Vector Machines Face and pedestrian detection AdaBoost Faces Building Fast Classifiers

Related searches for Learning and Vision: Discriminative Models

Download Presentation
## PowerPoint Slideshow about 'Learning and Vision: Discriminative Models' - euphemia

**An Image/Link below is provided (as is) to download presentation**

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript

### Learning and Vision:Discriminative Models

Chris Bishop and Paul Viola

Part II: Algorithms and Applications

- Part I: Fundamentals
- Part II: Algorithms and Applications
- Support Vector Machines
- Face and pedestrian detection

- AdaBoost
- Faces

- Building Fast Classifiers
- Trading off speed for accuracy…
- Face and object detection

- Memory Based Learning
- Simard
- Moghaddam

History Lesson

- 1950’s Perceptrons are cool
- Very simple learning rule, can learn “complex” concepts
- Generalized perceptrons are better -- too many weights

- 1960’s Perceptron’s stink (M+P)
- Some simple concepts require exponential # of features
- Can’t possibly learn that, right?

- Some simple concepts require exponential # of features
- 1980’s MLP’s are cool (R+M / PDP)
- Sort of simple learning rule, can learn anything (?)
- Create just the features you need

- 1990 MLP’s stink
- Hard to train : Slow / Local Minima

- 1996 Perceptron’s are cool

Why did we need multi-layer perceptrons?

- Problems like this seem to require very complex non-linearities.
- Minsky and Papert showed that an exponential number of features is necessary to solve generic problems.

MLP’s vs. Perceptron

- MLP’s are hard to train…
- Takes a long time (unpredictably long)
- Can converge to poor minima

- MLP are hard to understand
- What are they really doing?

- Perceptrons are easy to train…
- Type of linear programming. Polynomial time.
- One minimum which is global.

- Generalized perceptrons are easier to understand.
- Polynomial functions.

What about linearly inseparable?

Perceptron Training is Linear ProgrammingPolynomial time in the number of variables

and in the number of constraints.

Rebirth of Perceptrons

- How to train effectively
- Linear Programming (… later quadratic programming)
- Though on-line works great too.

- How to get so many features inexpensively?!?
- Kernel Trick

- How to generalize with so many features?
- VC dimension. (Or is it regularization?)

Lemma 1: Weight vectors are simple

- The weight vector lives in a sub-space spanned by the examples…
- Dimensionality is determined by the number of examples not the complexity of the space.

But Kernel Perceptrons CanGeneralize Poorly

Perceptron Rebirth: Generalization

- Too many features … Occam is unhappy
- Perhaps we should encourage smoothness?

Smoother

Linear Program is not unique

The linear program can return any multiple of the correct

weight vector...

Slack variables & Weight prior

- Force the solution toward zero

Definition of the Margin

- Geometric Margin: Gap between negatives and positives measured perpendicular to a hyperplane
- Classifier Margin

Require non-zero margin

Allows solutions

with zero margin

Enforces a non-zero

margin between examples

and the decision boundary.

Constrained Optimization

- Find the smoothest function that separates data
- Quadratic Programming (similar to Linear Programming)
- Single Minima
- Polynomial Time algorithm

- Quadratic Programming (similar to Linear Programming)

SVM: Key Ideas

- Augment inputs with a very large feature set
- Polynomials, etc.

- Use Kernel Trick(TM) to do this efficiently
- Enforce/Encourage Smoothness with weight penalty
- Introduce Margin
- Find best solution using Quadratic Programming

SVM: Zip Code recognition

- Data dimension: 256
- Feature Space: 4 th order
- roughly 100,000,000 dims

Classifier is Learned from Labeled Data

- Training Data
- 5000 faces
- All frontal

- 108 non faces
- Faces are normalized
- Scale, translation

- 5000 faces
- Many variations
- Across individuals
- Illumination
- Pose (rotation both in plane and out)

Key Properties of Face Detection

- Each image contains 10 - 50 thousand locs/scales
- Faces are rare 0 - 50 per image
- 1000 times as many non-faces as faces

- Extremely small # of false positives: 10-6

On to AdaBoost

- Given a set of weak classifiers
- None much better than random

- Iteratively combine classifiers
- Form a linear combination
- Training error converges to 0 quickly
- Test error is related to training margin

Classifier 1

Weights

Increased

Weak

Classifier 2

Weak

classifier 3

Final classifier is

linear combination of weak classifiers

Freund & Shapire

AdaBoostAdaBoost: Super Efficient Feature Selector

- Features = Weak Classifiers
- Each round selects the optimal feature given:
- Previous selected features
- Exponential Loss

Boosted Face Detection: Image Features

“Rectangle filters”

Similar to Haar wavelets

Papageorgiou, et al.

Unique Binary Features

Feature Selection

- For each round of boosting:
- Evaluate each rectangle filter on each example
- Sort examples by filter values
- Select best threshold for each filter (min Z)
- Select best filter/threshold (= Feature)
- Reweight examples

- M filters, T thresholds, N examples, L learning time
- O( MT L(MTN) ) Naïve Wrapper Method
- O( MN ) Adaboost feature selector

Example Classifier for Face Detection

A classifier with 200 rectangle features was learned using AdaBoost

95% correct detection on test set with 1 in 14084

false positives.

Not quite competitive...

ROC curve for 200 feature classifier

0

50

vs

false

neg

determined by

50 100

% Detection

T

T

T

T

IMAGE

SUB-WINDOW

Classifier 2

Classifier 3

FACE

Classifier 1

F

F

F

F

NON-FACE

NON-FACE

NON-FACE

NON-FACE

Building Fast Classifiers- Given a nested set of classifier hypothesis classes
- Computational Risk Minimization

Other Fast Classification Work

- Simard
- Rowley (Faces)
- Fleuret & Geman (Faces)

Cascaded Classifier

- A 1 feature classifier achieves 100% detection rate and about 50% false positive rate.
- A 5 feature classifier achieves 100% detection rate and 40% false positive rate (20% cumulative)
- using data from previous stage.

- A 20 feature classifier achieve 100% detection rate with 10% false positive rate (2% cumulative)

50%

20%

2%

IMAGE

SUB-WINDOW

5 Features

20 Features

FACE

1 Feature

F

F

F

NON-FACE

NON-FACE

NON-FACE

31

50

65

78

95

110

167

422

Viola-Jones

78.3

85.2

88.8

90.0

90.1

90.8

91.1

91.8

93.7

Rowley-Baluja-Kanade

83.2

86.0

89.2

90.1

89.9

Schneiderman-Kanade

94.4

Roth-Yang-Ahuja

(94.8)

Comparison to Other SystemsFalse Detections

Detector

Feature Localization

- Surprising properties of our framework
- The cost of detection is not a function of image size
- Just the number of features

- Learning automatically focuses attention on key regions

- The cost of detection is not a function of image size
- Conclusion: the “feature” detector can include a large contextual region around the feature

Feature Localization Features

- Learned features reflect the task

Andrew Moore

One-Nearest Neighbor…One nearest neighbor for fitting is described shortly…Similar to Join The Dots with two Pros and one Con.

- PRO: It is easy to implement with multivariate inputs.
- CON: It no longer interpolates locally.
- PRO: An excellent introduction to instance-based learning…

Andrew Moore

1-Nearest Neighbor is an example of….Instance-based learningFour things make a memory based learner:

- A distance metric
- How many nearby neighbors to look at?
- A weighting function (optional)
- How to fit with the local points?

x1y1

x2 y2

x3 y3

.

.

xn yn

A function approximator that has been around since about 1910.

To make a prediction, search database for similar datapoints, and fit with the local points.

Andrew Moore

Nearest NeighborFour things make a memory based learner:

- A distance metricEuclidian
- How many nearby neighbors to look at?One
- A weighting function (optional) Unused
- How to fit with the local points? Just predict the same output as the nearest neighbor.

Andrew Moore

Multivariate Distance MetricsSuppose the input vectors x1, x2, …xn are two dimensional:

x1 = ( x11 , x12 ) , x2 = ( x21 , x22) , …xN = ( xN1 , xN2 ).

One can draw the nearest-neighbor regions in input space.

The relative scalings in the distance metric affect region shapes.

Andrew Moore

Euclidean Distance MetricOther Metrics…

- Mahalanobis, Rank-based, Correlation-based (Stanfill+Waltz, Maes’ Ringo system…)

Or equivalently,

where

Simard: Tangent Distance

Baback Moghaddam

Euclidean (Standard) “Eigenfaces” Turk & Pentland (1992) Moghaddam & Pentland (1995)Projects all the training faces

onto a universal eigenspace

to “encode” variations (“modes”)

via principal components (PCA)

Uses inverse-distance

as a similarity measure

for matching & recognition

Baback Moghaddam

Euclidean Similarity Measures- Metric (distance-based) Similarity Measures
- template-matching, normalized correlation, etc

- Disadvantages
- Assumes isotropic variation (that all variations are equi-probable)
- Can not distinguish incidental changes from the critical ones
- Particularly bad for Face Recognition in which so many are incidental!
- for example: lighting and expression

PCA-Based Density Estimation Moghaddam & Pentland ICCV’95

Perform PCA and factorize into (orthogonal)

Gaussians subspaces:

Solve for minimal KL divergence residual for the orthogonal subspace:

Thanks to

Baback Moghaddam

See Tipping & Bishop (97) for an ML derivation within a more general factor analysis framework (PPCA)

Extrapersonal

dual subspaces for dyads (image pairs)

Equate “similarity” with posterior on

PCA-based density estimation

Moghaddam ICCV’95

Thanks to

Baback Moghaddam

Bayesian Face Recognition Moghaddam et al ICPR’96, FG’98, NIPS’99, ICCV’99smile

smile

light

specs

mouth

specs

smile

Intra

Extra

Standard

PCA

Thanks to

Baback Moghaddam

Intra-Extra (Dual) Subspaces

Thanks to

Baback Moghaddam

Two “pancake” subspaces with different orientations intersecting near the origin. If each is in fact Gaussian, then the optimal discriminant is hyperquadratic

Baback Moghaddam

Bayesian Similarity Measure- Bayesian (MAP) Similarity
- priors can be adjusted to reflect operational settings or used for Bayesian fusion (evidential “belief” from another level of inference)

- Likelihood (ML) Similarity

Intra-only (ML) recognition is only slightly inferior to MAP (by few %). Therefore, if you had to pick only one subspace to work in, you should pick Intra – and not standard eigenfaces!

FERET Identification: Pre-Test

Thanks to

Baback Moghaddam

Bayesian (Intra-Extra)

Standard (Eigenfaces)

..let’s leave distance metrics for now, and go back to….

Thanks to

Andrew Moore

One-Nearest NeighborObjection:

That noise-fitting is really objectionable.

What’s the most obvious way of dealing with it?

Andrew Moore

k-Nearest NeighborFour things make a memory based learner:

- A distance metricEuclidian
- How many nearby neighbors to look at?
k

- A weighting function (optional) Unused
- How to fit with the local points? Just predict the average output among the k nearest neighbors.

Andrew Moore

k-Nearest Neighbor (here k=9)K-nearest neighbor for function fitting smoothes away noise, but there are clear deficiencies.

What can we do about all the discontinuities that k-NN gives us?

Andrew Moore

Kernel RegressionFour things make a memory based learner:

- A distance metric Scaled Euclidian
- How many nearby neighbors to look at? All of them
- A weighting function (optional) wi = exp(-D(xi, query)2 / Kw2)
Nearby points to the query are weighted strongly, far points weakly. The KW parameter is the Kernel Width. Very important.

- How to fit with the local points? Predict the weighted average of the outputs:
predict = Σwiyi /Σwi

Andrew Moore

Kernel Regression in PicturesTake this dataset…

..and do a kernel prediction with xq (query) = 310, Kw = 50.

Andrew Moore

Varying the kernel widthIncreasing the kernel width Kw means further away points get an opportunity to influence you.

As Kwinfinity, the prediction tends to the global average.

Andrew Moore

Kernel Regression PredictionsIncreasing the kernel width Kw means further away points get an opportunity to influence you.

As Kwinfinity, the prediction tends to the global average.

Andrew Moore

Kernel Regression on our test casesChoosing a good Kw is important. Not just for Kernel Regression, but for all the locally weighted learners we’re about to see.

Andrew Moore

Weighting functionsLet

d=D(xi,xquery)/KW

Then here are some commonly used weighting functions…

(we use a Gaussian)

Andrew Moore

Locally Weighted RegressionKernel Regression:

Take a very very conservative function approximator called AVERAGING. Locally weight it.

Locally Weighted Regression:

Take a conservative function approximator called LINEAR REGRESSION. Locally weight it.

Let’s Review Linear Regression….

Andrew Moore

Unweighted Linear RegressionYou’re lying asleep in bed. Then Nature wakes you.

YOU: “Oh. Hello, Nature!”

NATURE: “I have a coefficient β in mind. I took a bunch of real numbers called x1, x2 ..xN thus: x1=3.1,x2=2, …xN=4.5.

For each of them (k=1,2,..N), I generated yk= βxk+εk

where εk is a Gaussian (i.e. Normal) random variable with mean 0 and standard deviation σ. The εk’s were generated independently of each other.

Here are the resulting yi’s: y1=5.1 , y2=4.2 , …yN=10.2”

You: “Uh-huh.”

Nature: “So what do you reckon β is then, eh?”

WHAT IS YOUR RESPONSE?

Andrew Moore

Locally Weighted RegressionFour things make a memory-based learner:

- A distance metric Scaled Euclidian
- How many nearby neighbors to look at? All of them
- A weighting function (optional) wk = exp(-D(xk, xquery)2 / Kw2) Nearby points to the query are weighted strongly, far points weakly. The Kwparameter is the Kernel Width.
- How to fit with the local points?
- First form a local linear model. Find the β that minimizes the locally weighted sum of squared residuals:

Then predict ypredict=βTxquery

Andrew Moore

How LWR worksQuery

Linear regression not flexible but trains like lightning.

Locally weighted regression is very flexible and fast to train.

Features, Features, Features

- In almost every case:
Good Features beat Good Learning

Learning beats No Learning

- Critical classifier ratio:
- AdaBoost >> SVM

Download Presentation

Connecting to Server..