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

Mengmi Zhang, Jiashi Feng, Keng Teck Ma, Joo Hwee Lim, Qi Zhao, Gabriel Kreiman

Research output: Contribution to journalArticlepeer-review

9 Scopus citations

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 on visual search 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 which can generalize to novel objects. The model provides an approximation to the mechanisms integrating bottom-up and top-down signals during search in natural scenes.

Original languageEnglish (US)
Article number3730
JournalNature communications
Volume9
Issue number1
DOIs
StatePublished - Dec 1 2018

Bibliographical note

Publisher Copyright:
© 2018, The Author(s).

Copyright:
Copyright 2019 Elsevier B.V., All rights reserved.

Fingerprint Dive into the research topics of 'Finding any Waldo with zero-shot invariant and efficient visual search'. Together they form a unique fingerprint.

Cite this