Unformatted text preview:

A simple classifier Ridge regression A variation on standard linear regression Adds a ridge term that has the effect of smoothing the weights Equivalent to training a linear network with weight decay A Strong Classifier SNoW Sparse Network of Winnows Roth et al 2000 Currently best reported face detector 1 Turn each pixel into a sparse binary vector 2 Activation sign wi xi 3 Train with the Winnow update rule AdaBoost for Feature Selection Viola and Jones 2001 used AdaBoost as a feature selection method For each round of AdaBoost For each patch train a classifier using only that one patch Select the best one as the classifier for this round reweight distribution based on that classifier Results 80 60 40 20 00 Single SNoW SNoW Bagging Ridge AdaBoost SNoW AdaBoost Ridge AdaBoost patches SNoW Bagging patches SNoW AdaBoost patches AdaBoost consistently improves performance 25 20 15 Single System Bagging AdaBoost 10 5 0 Global Ridge Global SNoW Patches Ridge Patches SNoW AdaBoost consistently improves performance 7 6 5 4 Single System Bagging AdaBoost 3 2 1 0 Global SNoW Patches Ridge Patches SNoW


View Full Document

UCSD CSE 291 - Simple Classifier

Documents in this Course
Bluegene

Bluegene

23 pages

TinyECC

TinyECC

19 pages

MultiNet

MultiNet

18 pages

Lecture 2

Lecture 2

23 pages

AdaBoost

AdaBoost

25 pages

Lecture 9

Lecture 9

46 pages

Lecture

Lecture

5 pages

GPSR

GPSR

18 pages

Load more
Loading Unlocking...
Login

Join to view Simple Classifier and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Simple Classifier and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?