Learning Location Invariance for Object Recognition and Localization

  • Gwendid T. van der Voort van der Kleij
  • Frank van der Velde
  • Marc de Kamps
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3704)


A visual system not only needs to recognize a stimulus, it also needs to find the location of the stimulus. In this paper, we present a neural network model that is able to generalize its ability to identify objects to new locations in its visual field. The model consists of a feedforward network for object identification and a feedback network for object location. The feedforward network first learns to identify simple features at all locations and therefore becomes selective for location invariant features. This network subsequently learns to identify objects partly by learning new conjunctions of these location invariant features. Once the feedforward network is able to identify an object at a new location, all conditions for supervised learning of additional, location dependent features for the object are set. The learning in the feedforward network can be transferred to the feedback network, which is needed to localize an object at a new location.


Object Recognition Neural Network Model Feedforward Network Oriented Line Feedback Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Van der Velde, F., de Kamps, M.: From knowing what to knowing where: Modeling object-based attention with feedback disinhibition of activation. Journal of Cognitive Neuroscience 13(4), 479–491 (2001)CrossRefGoogle Scholar
  2. 2.
    Fukushima, K.: Neocognitron capable of incremental learning. Neural Networks 17, 37–46 (2004)zbMATHCrossRefGoogle Scholar
  3. 3.
    Riesenhuber, M., Poggio, T.: Models of object recognition. Nature Neuroscience 3, 1199–1204 (2000)CrossRefGoogle Scholar
  4. 4.
    Itti, L., Koch, C.: A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research 40, 1489–1506 (2000)CrossRefGoogle Scholar
  5. 5.
    Amit, Y., Mascaro, M.: An integrated network for invariant visual detection and recognition. Vision Research 43, 2073–2088 (2003)CrossRefGoogle Scholar
  6. 6.
    Tanaka, K.: Representation of visual features of objects in the inferotemporal cortex. Neural Networks 9, 1459–1475 (1996)zbMATHCrossRefGoogle Scholar
  7. 7.
    Van der Voort van der Kleij, G.T., de Kamps, M., van der Velde, F.: A neural model of binding and capacity in visual working memory. In: Kaynak, O., Alpaydın, E., Oja, E., Xu, L. (eds.) ICANN 2003 and ICONIP 2003. LNCS, vol. 2714, pp. 771–778. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  8. 8.
    Sigman, M., Gilbert, C.D.: Learning to find a shape. Nature Neuroscience 3, 264–269 (2000)CrossRefGoogle Scholar
  9. 9.
    Ahissar, M., Hochstein, S.: The reverse hierarchy theory of visual perceptual learning. Trends in Cognitive Sciences 8(10), 457–464 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Gwendid T. van der Voort van der Kleij
    • 1
  • Frank van der Velde
    • 1
  • Marc de Kamps
    • 2
  1. 1.Cognitive Psychology UnitUniversity of LeidenLeidenThe Netherlands
  2. 2.Robotics and Embedded Systems, Department of InformaticsTechnische Universität MünchenGarching bei MünchenGermany

Personalised recommendations