Finding any Waldo: zero-shot invariant and efficient visual search
This addresses the challenge of visual search for novel objects without training, which is incremental as it builds on prior work focused on perfect matches after extensive training.
The paper tackles the problem of zero-shot invariant visual search for novel objects in cluttered scenes, showing that humans can do this efficiently and invariantly, and proposes a biologically inspired computational model that achieves this without exhaustive sampling.
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.