Please use this identifier to cite or link to this item: https://doi.org/10.1038/s41467-018-06217-x
Title: Finding any Waldo with zero-shot invariant and efficient visual search
Authors: Zhang M. 
Feng J. 
Ma K.T. 
Lim J.H. 
Zhao Q. 
Kreiman G.
Issue Date: 2018
Publisher: Nature Publishing Group
Citation: Zhang M., Feng J., Ma K.T., Lim J.H., Zhao Q., Kreiman G. (2018). Finding any Waldo with zero-shot invariant and efficient visual search. Nature Communications 9 (1) : 3730. ScholarBank@NUS Repository. https://doi.org/10.1038/s41467-018-06217-x
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. © 2018, The Author(s).
Source Title: Nature Communications
URI: http://scholarbank.nus.edu.sg/handle/10635/152122
ISSN: 20411723
DOI: 10.1038/s41467-018-06217-x
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
s41467-018-06217-x.pdf2.24 MBAdobe PDF

OPEN

NoneView/Download

SCOPUSTM   
Citations

1
checked on Nov 20, 2019

Page view(s)

114
checked on Nov 21, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.