Understanding Popout: Pre-attentive Segmentation through Nondirectional Repulsion

The goal of pre-attentive segmentation is to mark conspicuous image locations such as region boundaries, smooth contours and popout targets against backgrounds. This salience detection relies on not only feature similarity analysis but also local feature contrast. We identify these two measures with attraction and nondirectional repulsion, and unify the dual processes of association by attraction and segregation by repulsion in one grouping framework. We generalize normalized cuts to multi-way partitioning with these dual measures and show that the criterion can be viewed as a stochastic jump-diffusion process, where the probability of jump is determined by the relative strengths of attraction and repulsion. We demonstrate that this extended model can deal with salience detection under various situations as well as the asymmetry in visual search. Through these results, we provide a clear understanding of the role of negative weights in the graph partitioning framework. This opens up the possibilities of encoding negative correlations in constraint satisfaction problems, where solutions by simple and robust eigendecomposition become possible.