Conservative visual learning for object detection with minimal hand labeling effort

Authors:
Peter Roth;Helmut Grabner;Danijel Skočaj;Horst Bischof;Aleš Leonardis
Affiliations:
Inst. for Computer Graphics and Vision, Graz University of Technology, Austria;Inst. for Computer Graphics and Vision, Graz University of Technology, Austria;Faculty of Computer and Information Science, University of Ljubljana, Slovenia;Inst. for Computer Graphics and Vision, Graz University of Technology, Austria;Faculty of Computer and Information Science, University of Ljubljana, Slovenia
Venue:
PR'05 Proceedings of the 27th DAGM conference on Pattern Recognition
Year:
2005

Citing 15
Cited 2

The nature of statistical learning theory

The nature of statistical learning theory
A decision-theoretic generalization of on-line learning and an application to boosting

Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Neural Network-Based Face Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Example-Based Learning for View-Based Human Face Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust recognition using eigenimages

Computer Vision and Image Understanding - Special issue on robusst statistical techniques in image understanding
Linear Time Euclidean Distance Algorithms

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm

Machine Learning
A Robust PCA Algorithm for Building Representations from Panoramic Images

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
A Framework for Robust Subspace Learning

International Journal of Computer Vision - Special Issue on Computational Vision at Brown University
Unsupervised Improvement of Visual Detectors using Co-Training

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Detecting Pedestrians Using Patterns of Motion and Appearance

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Weighted and Robust Incremental Method for Subspace Learning

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Learning to Detect Objects in Images via a Sparse, Part-Based Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning object detection from a small number of examples: the importance of good features

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
An unsupervised, online learning framework for moving object detection

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition

Recognizing cars in aerial imagery to improve orthophotos

Proceedings of the 15th annual ACM international symposium on Advances in geographic information systems
Long term carefully learning for person detection application to intelligent surveillance system

Proceedings of the 9th International Conference on Advances in Mobile Computing and Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel framework for unsupervised training of an object detection system. The basic idea is to (1) exploit a huge amount of unlabeled video data by being very conservative in selecting training examples; and (2) to start with a very simple object detection system and using generative and discriminative classifiers in an iterative co-training fashion to arrive at increasingly better object detectors. We demonstrate the framework on a surveillance task where we learn a person detector. We start with a simple moving object classifier and proceed with robust PCA (on shape and appearance) as a generative classifier which in turn generates a training set for a discriminative AdaBoost classifier. The results obtained by AdaBoost are again filtered by PCA which produces an even better training set. We demonstrate that by using this approach we avoid hand labeling training data and still achieve a state of the art detection rate.