Learning a Fast Emulator of a Binary Decision Process Center for Machine Perception

Download 491 b.

Sana	04.08.2017
Hajmi	491 b.
	#12752

Learning a Fast Emulator of a Binary Decision Process

Center for Machine Perception
Czech Technical University, Prague
ACCV 2007, Tokyo, Japan

Importance of Classification Speed

Time-to-decision vs. precision trade-off is inherent in many detection, recognition and matching problems in computer vision
Often the trade-off is not explicitly stated in the problem formulation, but decision time clearly influences impact of a method
Example: face detection

Viola-Jones (2001) – real-time performance

2500 citations

Schneiderman-Kanade (1998) - smaller error rates, but 1000x slower

250 citations

Fast Emulation of A Decision Process

The Idea
Given a black box algorithm A performing some useful binary decision task
Train a sequential classifier S to (approximately) emulate detection performance of algorithm A while minimizing time-to-decision
Allow user to control quality of the approximation
Contribution
A general framework for speeding up existing algorithms by a sequential classifier learned by the WaldBoost algorithm [1]
Demonstrated on two interest point detectors
Advantages
Instead of spending man-months on code optimization, choose relevant feature class and train sequential classifier S
Your (slow) Matlab code can be speeded up this way!
[1] J. Šochman and J. Matas. Waldboost – Learning For Time Constrained Sequential Detection. CVPR 2005

Black-box Generated Training Set

WaldBoost Optimization Task

Basic notions:
Sequential strategy S is characterized by:
Problem formulation:

WaldBoost Sequential Classifier Training

Combines AdaBoost training (provides measurements) with Wald’s sequential decision making theory (for sequential decisions)
Sequential WaldBoost classifier
Set of weak classifiers (features) and thresholds are found during training

Emulation of Similarity-Invariant Regions

Motivation
Hessian-Laplace is close to state of the art
Kadir’s detector very slow (100x slower than Difference of Gaussians)
Standard testing protocol exists
Executables of both methods available at robots.ox.ac.uk
Both detectors are scale-invariant which is easily implemented via a scanning window + a sequential test
Implementation
Choice of : various filters computable with integral images - difference of rectangular regions, variance in a window
Positive samples: Patches twice the size of original interest point scale

Results: Hessian-Laplace – boat sequence

Results: Kadir-Brady – east-south sequence

Repeatability slightly higher (left graph)
Matching score slightly higher (middle graph)
Higher number of correspondences and correct matches in WaldBoost.
Speed comparison (850x680 image)

Approximation Quality – Hesian-Laplace

Yellow circles: repeated detections (85% coverage)
Red circles: original detections not found by the WaldBoost detector

Approximation Quality – Kadir-Brady

Yellow circles: repeated detections (96% coverage)
Red circles: original detections not found by the WaldBoost detector

Conclusions and Future Work

A general framework for speeding up existing binary decision algorithms has been presented
To optimize the emulator’s time-to-decision a WaldBoost sequential classifier was trained
The approach was demonstrated on (but is not limited to) two interest point detectors emulation
Future work
Precise localization of the detections by interpolation on the grid
Using real value output of the black-box algorithm (“sequential regression”)
To emulate or to be repeatable?

Conclusions and Future Work

A general framework for speeding up existing binary decision algorithms has been presented
To optimize the emulator’s time-to-decision a WaldBoost sequential classifier was trained
The approach was demonstrated (but is not limited to) on two interest point detectors
Future work
Precise localization of the detections by interpolation on the grid
Using real value output of the black-box algorithm (“sequential regression”)
To emulate or to be repeatable?
Thank you for your attention

Download 491 b.

Do'stlaringiz bilan baham:

Learning a Fast Emulator of a Binary Decision Process Center for Machine Perception

Learning a Fast Emulator of a Binary Decision Process

Center for Machine Perception

Czech Technical University, Prague

ACCV 2007, Tokyo, Japan

Importance of Classification Speed

Time-to-decision vs. precision trade-off is inherent in many detection, recognition and matching problems in computer vision

Often the trade-off is not explicitly stated in the problem formulation, but decision time clearly influences impact of a method

Example: face detection

Fast Emulation of A Decision Process

The Idea

Given a black box algorithm A performing some useful binary decision task

Train a sequential classifier S to (approximately) emulate detection performance of algorithm A while minimizing time-to-decision

Allow user to control quality of the approximation

Contribution

A general framework for speeding up existing algorithms by a sequential classifier learned by the WaldBoost algorithm [1]

Demonstrated on two interest point detectors

Advantages

Instead of spending man-months on code optimization, choose relevant feature class and train sequential classifier S

Your (slow) Matlab code can be speeded up this way!

[1] J. Šochman and J. Matas. Waldboost – Learning For Time Constrained Sequential Detection. CVPR 2005

Black-box Generated Training Set

WaldBoost Optimization Task

Basic notions:

Sequential strategy S is characterized by:

Problem formulation:

WaldBoost Sequential Classifier Training

Combines AdaBoost training (provides measurements) with Wald’s sequential decision making theory (for sequential decisions)

Sequential WaldBoost classifier

Set of weak classifiers (features) and thresholds are found during training

Emulation of Similarity-Invariant Regions

Motivation

Hessian-Laplace is close to state of the art

Kadir’s detector very slow (100x slower than Difference of Gaussians)

Standard testing protocol exists

Executables of both methods available at robots.ox.ac.uk

Both detectors are scale-invariant which is easily implemented via a scanning window + a sequential test

Implementation

Choice of : various filters computable with integral images - difference of rectangular regions, variance in a window

Positive samples: Patches twice the size of original interest point scale

Results: Hessian-Laplace – boat sequence

Results: Kadir-Brady – east-south sequence

Repeatability slightly higher (left graph)

Matching score slightly higher (middle graph)

Higher number of correspondences and correct matches in WaldBoost.

Speed comparison (850x680 image)

Approximation Quality – Hesian-Laplace

Yellow circles: repeated detections (85% coverage)

Red circles: original detections not found by the WaldBoost detector

Approximation Quality – Kadir-Brady

Yellow circles: repeated detections (96% coverage)

Red circles: original detections not found by the WaldBoost detector

Conclusions and Future Work

A general framework for speeding up existing binary decision algorithms has been presented

To optimize the emulator’s time-to-decision a WaldBoost sequential classifier was trained

The approach was demonstrated on (but is not limited to) two interest point detectors emulation

Future work

Precise localization of the detections by interpolation on the grid

Using real value output of the black-box algorithm (“sequential regression”)

To emulate or to be repeatable?

Conclusions and Future Work

A general framework for speeding up existing binary decision algorithms has been presented

To optimize the emulator’s time-to-decision a WaldBoost sequential classifier was trained

The approach was demonstrated (but is not limited to) on two interest point detectors

Future work

Precise localization of the detections by interpolation on the grid

Using real value output of the black-box algorithm (“sequential regression”)

To emulate or to be repeatable?

Thank you for your attention