Abstract
For novel class identification we propose to rely on the natural hierarchy of object classes, using a new approach to detect incongruent events. Here detection is based on the discrepancy between the responses of two different classifiers trained at different levels of generality: novelty is detected when the general level classifier accepts, and the specific level classifier rejects. Thus our approach is arguably more robust than traditional approaches to novelty detection, and more amendable to effective information transfer between known and new classes.We present an algorithmic implementation of this approach, show experimental results of its performance, analyze the effect of the underlying hierarchy on the task and show the benefit of using discriminative information for the training of the specific level classifier.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bar-Hillel, A., Hertz, T., Weinshall, D.: Efficient learning of relational object class models. In: ICCV (2005)
Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset. Technical Report UCB/CSD-04-1366, California Institute of Technology (2007)
Leibe, B., Leonardis, A., Schiele, B.: Robust object detection with interleaved categorization and segmentation. IJCV 77(1), 259–289 (2008)
Markou, M., Singh, S.: Novelty detection: a review-part 1: statistical approaches. Signal Processing 83(12), 2481–2497 (2003)
Markou, M., Singh, S.: Novelty detection: a review-part 2: neural network based approaches. Signal Processing 83(12), 2499–2521 (2003)
Weinshall, D., Hermansky, H., Zweig, A., Luo, J., Jimison, H., Frank, O., Povel, M.: Beyond Novelty Detection: Incongruent Events, when General and Specific Classifiers Disagree. In: NIPS (2008)
Zweig, A., Weinshall, D.: Exploiting Object Hierarchy: Combining Models from Different Category Levels. In: ICCV (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Zweig, A., Eshar, D., Weinshall, D. (2012). Identification of Novel Classes in Object Class Recognition. In: Weinshall, D., Anemüller, J., van Gool, L. (eds) Detection and Identification of Rare Audiovisual Cues. Studies in Computational Intelligence, vol 384. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24034-8_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-24034-8_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24033-1
Online ISBN: 978-3-642-24034-8
eBook Packages: EngineeringEngineering (R0)