Finding any Waldo: zero-shot invariant and efficient visual search

TL;DR

This paper demonstrates that humans can efficiently and invariantly search for natural objects in complex scenes and introduces a biologically inspired model that performs zero-shot visual search without exhaustive sampling.

Contribution

It presents the first computational model capable of zero-shot, invariant visual search in complex scenes, inspired by biological mechanisms.

Findings

Humans can efficiently find natural objects invariant to appearance changes.

The proposed model approximates biological search mechanisms.

Model generalizes to novel objects without training on specific categories.

Abstract

Searching for a target object in a cluttered scene constitutes a fundamental challenge in daily vision. Visual search must be selective enough to discriminate the target from distractors, invariant to changes in the appearance of the target, efficient to avoid exhaustive exploration of the image, and must generalize to locate novel target objects with zero-shot training. Previous work has focused on searching for perfect matches of a target after extensive category-specific training. Here we show for the first time that humans can efficiently and invariantly search for natural objects in complex scenes. To gain insight into the mechanisms that guide visual search, we propose a biologically inspired computational model that can locate targets without exhaustive sampling and generalize to novel objects. The model provides an approximation to the mechanisms integrating bottom-up and top-down signals during search in natural scenes.