Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)
Paul Sajda, Leif Finkel
We propose that the binding and segmentation of visual features is mediated by two complementary mechanisms; a low resolu(cid:173) tion, spatial-based, resource-free process and a high resolution, temporal-based, resource-limited process. In the visual cortex, the former depends upon the orderly topographic organization in stri(cid:173) ate and extrastriate areas while the latter may be related to ob(cid:173) served temporal relationships between neuronal activities . Com(cid:173) puter simulations illustrate the role the two mechanisms play in figure/ ground discrimination, depth-from-occlusion, and the vivid(cid:173) ness of perceptual completion.
1 COMPLEMENTARY BINDING MECHANISMS
The "binding problem" is a classic problem in computational neuroscience which considers how neuronal activities are grouped to create mental representations. For the case of visual processing, the binding of neuronal activities requires a mecha(cid:173) nism for selectively grouping fragmented visual features in order to construct the coherent representations (i.e. objects) which we perceive. In this paper we argue for the existence of two complementary mechanisms for neural binding, and we show how such mechanisms may operate in the constructiO:l of intermediate-level visual representations.