Unsupervised improvement of visual detectors using cotraining

One significant challenge in the construction of visual detection systems is the acquisition of sufficient labeled data. We describe a new technique for training visual detectors which requires only a small quantity of labeled data, and then uses unlabeled data to improve performance over time. Unsupervised improvement is based on the cotraining framework of Blum and Mitchell, in which two disparate classifiers are trained simultaneously. Unlabeled examples which are confidently labeled by one classifier are added, with labels, to the training set of the other classifier. Experiments are presented on the realistic task of automobile detection in roadway surveillance video. In this application, cotraining reduces the false positive rate by a factor of 2 to 11 from the classifier trained with labeled data alone.

[1]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[2]  Yoav Freund,et al.  Boosting the margin: A new explanation for the effectiveness of voting methods , 1997, ICML.

[3]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[4]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Michael I. Jordan,et al.  Unsupervised Learning from Dyadic Data , 1998 .

[6]  Tomaso A. Poggio,et al.  A general framework for object detection , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[7]  Yoram Singer,et al.  Unsupervised Models for Named Entity Classification , 1999, EMNLP.

[8]  Thorsten Joachims,et al.  Transductive Inference for Text Classification using Support Vector Machines , 1999, ICML.

[9]  Yoav Freund,et al.  A Short Introduction to Boosting , 1999 .

[10]  Takeo Kanade,et al.  A statistical method for 3D object detection applied to faces and cars , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[11]  Tommi S. Jaakkola,et al.  Kernel Expansions with Unlabeled Examples , 2000, NIPS.

[12]  Paul A. Viola,et al.  Robust Real-time Object Detection , 2001 .

[13]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[14]  Byoung-Tak Zhang,et al.  Document filtering boosted by unlabeled data , 2001, ISIE 2001. 2001 IEEE International Symposium on Industrial Electronics Proceedings (Cat. No.01TH8570).

[15]  Neil A. Dodgson,et al.  Proceedings Ninth IEEE International Conference on Computer Vision , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[16]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[17]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[18]  Sebastian Thrun,et al.  Text Classification from Labeled and Unlabeled Documents using EM , 2000, Machine Learning.