Selective Attention in the Learning of Viewpoint and Position Invariance
- 1.2k Downloads
Selective attention plays an important role in visual processing in reducing the problem scale and in actively gathering useful information. We propose a modified saliency map mechanism that uses a simple top-down task-dependent cue to allow attention to stay mainly on one object in the scene each time for the first few shifts. Such a method allows the learning of invariant object representations across attention shifts in a multiple-object scene. In this paper, we construct a neural network that can learn position and viewpoint invariant representations for objects across attention shifts in a temporal sequence.
KeywordsBody Motion Local Feature Selective Attention Sparse Code Attention Shift
Unable to display preview. Download preview PDF.
- 1.Bülthoff, H.H., Wallraven, C., Graf, A.B.A.: View-based dynamic object recognition based on human perception. In: Proceedings of 16th International Conference on pattern recognition, vol. 3, pp. 768–776 (2002)Google Scholar
- 3.Clark, J.J., O’Regan, J.K.: A Temporal-difference learning model for perceptual stability in color vision. In: Proceedings of 15th International Conference on Pattern Recognition, vol. 2, pp. 503–506 (2000)Google Scholar
- 5.Hafed, Z.M.: Motor theories of attention: How action serves perception in the visual system. Ph.D Thesis, McGill University, Canada (2003)Google Scholar
- 8.Koch, C., Ullman, S.: Shifts in selective visual attention: Towards the underlying neural circuitry. Human Neurobiology 4, 219–227 (1985)Google Scholar
- 14.Olshausen, B.A., Anderson, C.H., Van Essen, D.C.: A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. The Journal of Neuroscience 13(11), 4700–4719 (1993)Google Scholar
- 16.Rumelhart, D.I., Zipser, D.: A complex-cell receptive-filed model. Journal of Neurophysiology 53, 1266–1286 (1985)Google Scholar