Constellations: A novel dataset for studying iterative inference in humans and AI

Under complex viewing conditions, human perception relies on generating hypotheses and revising them in an iterative fashion. We developed novel visual stimuli to study such iterative inference in humans and AI. In these stimuli, called "constellations", all local information about the obj...

Full description

Saved in:

Bibliographic Details
Published in:	2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) pp. 5138 - 5148
Main Authors:	Khajuria, Tarun, Tulver, Kadi, Luik, Taavi, Aru, Jaan
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-06-2022
Subjects:	Conferences Image recognition Inference algorithms Iterative algorithms Machine vision Refining Visualization
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Under complex viewing conditions, human perception relies on generating hypotheses and revising them in an iterative fashion. We developed novel visual stimuli to study such iterative inference in humans and AI. In these stimuli, called "constellations", all local information about the object has been removed and it can only be recognized when taking into account the global pattern. We here describe the dataset and demonstrate that humans indeed use an iterative process of generating hypotheses and refining them to solve these images. We also provide code that allows researchers to create their own constellation images. The constellation dataset allows researchers to develop sketching algorithms for guessing the hidden object. As such algorithms used by humans appear to be iterative in nature, this dataset will facilitate the study of iterative inference in minds and machines.
ISSN:	2160-7516
DOI:	10.1109/CVPRW56347.2022.00562