Probabilistic Computations for Attention, Eye Movements, and Search

The term visual attention immediately evokes the idea of limited resources, serial processing, or a zoom metaphor. But evidence has slowly accumulated that computations that take into account probabilistic relationships among visual forms and the target contribute to optimizing decisions in biological and artificial organisms, even without considering these limited-capacity processes in covert attention or even foveation. The benefits from such computations can be formalized within the framework of an ideal Bayesian observer and can be related to the classic theory of sensory cue combination in vision science and context- driven approaches to object detection in computer vision. The framework can account for a large range of behavioral findings across distinct experimental paradigms, including visual search, cueing, and scene context. I argue that these forms of probabilistic computations might be fundamental to optimizing decisions in many species and review human experiments trying to identify scene properties that serve as cues to guide eye movements and facilitate search. I conclude by discussing contributions of attention beyond probabilistic computations but argue that the framework's merit is to unify many basic paradigms to study attention under a single theory.