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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Unsupervised improvement of visual detectors using cotraining


    Contributors:
    Levin, (author) / Viola, (author) / Freund, (author)


    Publication date :

    2003-01-01


    Size :

    548006 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Unsupervised Improvement of Visual Detectors Using Co-Training

    Levin, A. / Viola, P. / Freund, Y. et al. | British Library Conference Proceedings | 2003


    Driver Visual Distraction Detection Using Unsupervised Learning Techniques

    Hamieh, Salam / Heiries, Vincent / Al-Osman, Hussein et al. | IEEE | 2023


    Unsupervised Monocular Visual Odometry Based on Confidence Evaluation

    Liu, Yiling / Wang, Hesheng / Wang, Jingchuan et al. | IEEE | 2022


    Model Selection for Unsupervised Learning of Visual Context

    Xiang, T. / Gong, S. | British Library Online Contents | 2006


    Unsupervised and simultaneous training of multiple object detectors from unlabeled surveillance video

    Celik, H. / Hanjalic, A. / Hendriks, E. A. | British Library Online Contents | 2009