Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kotseruba, Iuliia, Wloka, Calden, Rasouli, Amir, Tsotsos, John K.
Format: Preprint
Veröffentlicht: 2020
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910695791001600
author Kotseruba, Iuliia
Wloka, Calden
Rasouli, Amir
Tsotsos, John K.
author_facet Kotseruba, Iuliia
Wloka, Calden
Rasouli, Amir
Tsotsos, John K.
contents Recent advances in the field of saliency have concentrated on fixation prediction, with benchmarks reaching saturation. However, there is an extensive body of works in psychology and neuroscience that describe aspects of human visual attention that might not be adequately captured by current approaches. Here, we investigate singleton detection, which can be thought of as a canonical example of salience. We introduce two novel datasets, one with psychophysical patterns and one with natural odd-one-out stimuli. Using these datasets we demonstrate through extensive experimentation that nearly all saliency algorithms do not adequately respond to singleton targets in synthetic and natural images. Furthermore, we investigate the effect of training state-of-the-art CNN-based saliency models on these types of stimuli and conclude that the additional training data does not lead to a significant improvement of their ability to find odd-one-out targets. Datasets are available at http://data.nvision2.eecs.yorku.ca/P3O3/.
format Preprint
id arxiv_https___arxiv_org_abs_2005_06583
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations
Kotseruba, Iuliia
Wloka, Calden
Rasouli, Amir
Tsotsos, John K.
Computer Vision and Pattern Recognition
Recent advances in the field of saliency have concentrated on fixation prediction, with benchmarks reaching saturation. However, there is an extensive body of works in psychology and neuroscience that describe aspects of human visual attention that might not be adequately captured by current approaches. Here, we investigate singleton detection, which can be thought of as a canonical example of salience. We introduce two novel datasets, one with psychophysical patterns and one with natural odd-one-out stimuli. Using these datasets we demonstrate through extensive experimentation that nearly all saliency algorithms do not adequately respond to singleton targets in synthetic and natural images. Furthermore, we investigate the effect of training state-of-the-art CNN-based saliency models on these types of stimuli and conclude that the additional training data does not lead to a significant improvement of their ability to find odd-one-out targets. Datasets are available at http://data.nvision2.eecs.yorku.ca/P3O3/.
title Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2005.06583