Unsupervised Improvement of Visual Detectors using Co-Training

Authors:
Anat Levin;Paul Viola;Yoav Freund
Affiliations:
-;-;-
Venue:
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Year:
2003

Citing 0
Cited 36

Object tracking: A survey

ACM Computing Surveys (CSUR)
Co-Adaptation of audio-visual speech and gesture classifiers

Proceedings of the 8th international conference on Multimodal interfaces
Multistrategical image classification for image data mining

Proceedings of the 8th international workshop on Multimedia data mining: (associated with the ACM SIGKDD 2007)
The value of agreement a new boosting algorithm

Journal of Computer and System Sciences
Watch, Listen & Learn: Co-training on Captioned Images and Videos

ECML PKDD '08 Proceedings of the 2008 European Conference on Machine Learning and Knowledge Discovery in Databases - Part I
Object Tracking Using Grayscale Appearance Models and Swarm Based Particle Filter

HAIS '08 Proceedings of the 3rd international workshop on Hybrid Artificial Intelligence Systems
Agnostic active learning

Journal of Computer and System Sciences
Automatic Database Creation and Object's Model Learning

Knowledge Acquisition: Approaches, Algorithms and Applications
Unsupervised and simultaneous training of multiple object detectors from unlabeled surveillance video

Computer Vision and Image Understanding
A discriminative model for semi-supervised learning

Journal of the ACM (JACM)
Vehicle tracking based on co-learning particle filter

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
MAPACo-training: a novel online learning algorithm of behavior models

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Multistrategical approach in visual learning

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Learning-based object tracking using boosted features and appearance-adaptive models

ACIVS'07 Proceedings of the 9th international conference on Advanced concepts for intelligent vision systems
Learning to recognize objects from unseen modalities

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Improving object classification in far-field video

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
On-line multi-view forests for tracking

Proceedings of the 32nd DAGM conference on Pattern recognition
Robust multi-view boosting with priors

ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Combining committee-based semi-supervised learning and active learning

Journal of Computer Science and Technology
Online multiple instance boosting for object detection

Neurocomputing
Boosted multi-class semi-supervised learning for human action recognition

Pattern Recognition
Efficient learning by combining confidence-rated classifiers to incorporate unlabeled medical data

MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Conservative visual learning for object detection with minimal hand labeling effort

PR'05 Proceedings of the 27th DAGM conference on Pattern Recognition
The value of agreement, a new boosting algorithm

COLT'05 Proceedings of the 18th annual conference on Learning Theory
A PAC-Style model for learning from labeled and unlabeled data

COLT'05 Proceedings of the 18th annual conference on Learning Theory
On-line inverse multiple instance boosting for classifier grids

Pattern Recognition Letters
DCPE co-training for classification

Neurocomputing
Bootstrapping Boosted Random Ferns for discriminative and efficient object classification

Pattern Recognition
Transductive relational classification in the co-training paradigm

MLDM'12 Proceedings of the 8th international conference on Machine Learning and Data Mining in Pattern Recognition
Semantic video content annotation at the object level

Proceedings of the 10th International Conference on Advances in Mobile Computing & Multimedia
A survey of appearance models in visual object tracking

ACM Transactions on Intelligent Systems and Technology (TIST) - Survey papers, special sections on the semantic adaptive social web, intelligent systems for health informatics, regular papers
Model probability in self-organising maps

IWANN'13 Proceedings of the 12th international conference on Artificial Neural Networks: advences in computational intelligence - Volume Part II
An Embedded Co-AdaBoost based construction of software document relation coupled resource spaces for cyber-physical society

Future Generation Computer Systems
Kernel-based transition probability toward similarity measure for semi-supervised learning

Pattern Recognition
Co-trained generative and discriminative trackers with cascade particle filter

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

One significant challenge in the construction of visualdetection systems is the acquisition of sufficient labeleddata. This paper describes a new technique for trainingvisual detectors which requires only a small quantity of labeleddata, and then uses unlabeled data to improve performanceover time. Unsupervised improvement is based onthe co-training framework of Blum and Mitchell, in whichtwo disparate classifiers are trained simultaneously. Unlabeledexamples which are confidently labeled by one classifierare added, with labels, to the training set of the otherclassifier. Experiments are presented on the realistic task ofautomobile detection in roadway surveillance video. In thisapplication, co-training reduces the false positive rate by afactor of 2 to 11 from the classifier trained with labeled dataalone.