The Secrets of Salient Object Segmentation

In this paper we provide an extensive evaluation of fixation prediction and salient object segmentation algorithms as well as statistics of major datasets. Our analysis identifies serious design flaws of existing salient object benchmarks, called the dataset design bias, by over emphasising the ster...

Full description

Saved in:
Bibliographic Details
Published in:2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 280 - 287
Main Authors: Yin Li, Xiaodi Hou, Koch, Christof, Rehg, James M., Yuille, Alan L.
Format: Conference Proceeding Journal Article
Language:English
Published: IEEE 01.06.2014
Subjects:
Algorithm design and analysis
Algorithms
Benchmark testing
Benchmarks
Bias
Computer vision
dataset analysis
Design engineering
eye fixation
Fixation
Image color analysis
Image segmentation
Labeling
Object segmentation
Pattern recognition
Prediction algorithms
Saliency
salient object segmentation
Segmentation
Statistics
ISSN:1063-6919, 1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we provide an extensive evaluation of fixation prediction and salient object segmentation algorithms as well as statistics of major datasets. Our analysis identifies serious design flaws of existing salient object benchmarks, called the dataset design bias, by over emphasising the stereotypical concepts of saliency. The dataset design bias does not only create the discomforting disconnection between fixations and salient object segmentation, but also misleads the algorithm designing. Based on our analysis, we propose a new high quality dataset that offers both fixation and salient object segmentation ground-truth. With fixations and salient object being presented simultaneously, we are able to bridge the gap between fixations and salient objects, and propose a novel method for salient object segmentation. Finally, we report significant benchmark progress on 3 existing datasets of segmenting salient objects.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2014.43