Abstract


= PDF Reprint,     = BibTeX entry,     = Online Abstract


Click to download PDF version Click to download BibTeX data Clik to view abstract D. Walther, M. Riesenhuber, T. Poggio, L. Itti, C. Koch, Towards an integrated model of saliency-based attention and object recognition in the primate's visual system, In: Journal of Cognitive Neuroscience, Vol. B14, No. S, pp. 46-47, Apr 2002. (Cited by 10)

Abstract: We present an integrated model for the dorsal (where) and the ventral (what) pathway in the primate's visual processing system and the interaction between these two pathways. To reach our goal of modeling visual search behavior in primates, we integrate and extend the saliency-based model for bottom-up attention by Itti and Koch (Nat. Rev. Neurosci. 2001;2(3):194-203) and the HMAX hierarchical model for object recognition by Riesenhuber and Poggio (Nat. Neurosci. 1999;2:1019-1025). In the combined model we use saliency-based attention to modulate object recognition at the V4 level. Interesting regions in the visual scene are successively selected by a rapidly shiftable focus of attention (FOA). Neural activity of a particular neuron in V4 is inhibited based on its distance from the current FOA. Recognition rates for stimuli composed of two paper clip objects typically increase twofold compared to previous experiments without attention (Neuron 1999;24(1):87-93). To achieve this improvement a depression of the V4 activity outside the focus of attention by as little as 20% proves to be sufficient. With 10% activity modulation recognition still improves by 70%. We find that the twofold increase in recognition rate is robust over a large range of modulation strengths of the V4 activity. We conclude that a rather weak attentional modulation of the neural activity at the V4 level suffices to recognize multiple objects in the same display. Our model will be extended to search for specific objects in cluttered natural scenes and include biasing of the attention system in a top-down manner.

Themes: Computational Modeling, Model of Bottom-Up Saliency-Based Visual Attention

 

Copyright © 2000-2007 by the University of Southern California, iLab and Prof. Laurent Itti.
This page generated by bibTOhtml on Wed Feb 15 12:13:56 PST 2017