Automatic cascade training with perturbation bias

Authors:
Jie Sun;James M. Rehg;Aaron Bobick
Affiliations:
GVU Center, College of Computing, Georgia Institute of Technology;GVU Center, College of Computing, Georgia Institute of Technology;GVU Center, College of Computing, Georgia Institute of Technology
Venue:
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Year:
2004

Citing 9
Cited 8

Joint Induction of Shape Features and Tree Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Network-Based Face Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Antifaces: A Novel, Fast Method for Image Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Detecting Faces in Images: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Rejection

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Finding faces in cluttered scenes using random labeled graph matching

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
A statistical approach to 3d object detection applied to faces and cars

A statistical approach to 3d object detection applied to faces and cars
Boosting Chain Learning for Object Detection

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Kullback-leibler boosting

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition

Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle

International Journal of Computer Vision
On the Design of Cascades of Boosted Ensembles for Face Detection

International Journal of Computer Vision
Multi-view fast object detection by using extended haar filters in uncontrolled environments

Pattern Recognition Letters
Fast learning for statistical face detection

ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
Towards optimal training of cascaded detectors

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Learning to detect objects of many classes using binary classifiers

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
A binary decision tree implementation of a boosted strong classifier

AMFG'05 Proceedings of the Second international conference on Analysis and Modelling of Faces and Gestures
Human detection using oriented histograms of flow and appearance

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Face detection methods based on a cascade architecture have demonstrated fast and robust performance. Cascade learning is aided by the modularity of the architecture in which nodes are chained together to form a cascade. In this paper we present two new cascade learning results which address the decoupled nature of the cascade learning task. First, we introduce a cascade indifference curve framework which connects the learning objectives for a node to the overall cascade performance. We derive a new cost function for node learning which yields fully-automatic stopping conditions and improved detection performance. Second, we introduce the concept of perturbation bias which leverages the statistical differences between target and nontarget classes in a detection problem to obtain improved performance and robustness. We derive necessary and sufficient conditions for the success of the method and present experimental results.