Many state of the art object classification applications require many data samples, whose collection is usually a very costly process. Performing initial model training with synthetic samples (from virtual reality tools) has been proposed as a possible solution, although the resulting classification models need to be adapted (fine-tuned) to real-world data afterwards. For this bootstrapping process, we propose to use an incremental learning algorithm from the cognitive robotics domain which is particularly suited for perceptual problems. We apply it to a pedestrian detection problem where a synthetic dataset is used for initial training, and two different real-world datasets for fine-tuning and evaluation. The proposed scheme greatly reduces the number of real-world samples required while maintaining high classification accuracy. We additionally demonstrate several innovative incremental learning schemes for object detection, the basic idea being that usually only very few background samples are actually similar to pedestrian samples. By suitable arrangement of incremental learning steps, we can keep classification models simple by representing only such “hard” background samples.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Incremental learning for bootstrapping object classifier models


    Contributors:


    Publication date :

    2016-11-01


    Size :

    1247258 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Bootstrapping color constancy

    Funt, B. V. / Cardei, V. C. / SPIE et al. | British Library Conference Proceedings | 1999


    Incremental Learning of Novel Resident Space Object Spectral Fingerprints

    Gazak, J. Zachary | British Library Conference Proceedings | 2021


    Incremental learning of human activity models from videos

    Hasan, Mahmudul / Roy-Chowdhury, Amit K. | British Library Online Contents | 2016


    Incremental learning of human activity models from videos

    Hasan, Mahmudul / Roy-Chowdhury, Amit K. | British Library Online Contents | 2016


    Incremental learning of human activity models from videos

    Hasan, Mahmudul / Roy-Chowdhury, Amit K. | British Library Online Contents | 2016