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

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.

arXiv commentNumber of figures: 6 Number of supplementary figures: 14

References in corpus (1)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Cited by in corpus (6)

• Look Twice: A Generalist Computational Model Predicts Return Fixations across Tasks and Species
• Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases
• CNN-based search model underestimates attention guidance by simple visual features
• Lift-the-flap: what, where and when for context reasoning
• Modeling human visual search: A combined Bayesian searcher and saliency map approach for eye movement guidance in natural scenes
• What am I Searching for: Zero-shot Target Identity Inference in Visual Search