Wave Propagation of Visual Stimuli in Focus of Attention

TL;DR

This paper introduces a biologically-inspired computational model of visual attention that uses wave propagation to efficiently predict focus shifts, aligning with biological principles and achieving high accuracy in scanpath prediction.

Contribution

The paper presents a novel wave propagation-based model of attention that is biologically plausible, parallelizable, and reduces to existing models at high wave velocities.

Findings

Achieves top-level performance in scanpath prediction tasks.

Model exhibits spatiotemporal locality and inhibition of return.

Reduces to gravitational models as wave velocity increases.

Abstract

Fast reactions to changes in the surrounding visual environment require efficient attention mechanisms to reallocate computational resources to most relevant locations in the visual field. While current computational models keep improving their predictive ability thanks to the increasing availability of data, they still struggle approximating the effectiveness and efficiency exhibited by foveated animals. In this paper, we present a biologically-plausible computational model of focus of attention that exhibits spatiotemporal locality and that is very well-suited for parallel and distributed implementations. Attention emerges as a wave propagation process originated by visual stimuli corresponding to details and motion information. The resulting field obeys the principle of "inhibition of return" so as not to get stuck in potential holes. An accurate experimentation of the model shows that it achieves top level performance in scanpath prediction tasks. This can easily be understood at the light of a theoretical result that we establish in the paper, where we prove that as the velocity of wave propagation goes to infinity, the proposed model reduces to recently proposed state of the art gravitational models of focus of attention.