We provide a comprehensive evaluation of salient object detection (SOD) models. Our analysis identifies a serious design bias of existing SOD datasets which assumes that each image contains at least one clearly outstanding salient object in low clutter. The design bias has led to a saturated high performance for state-of-the-art SOD models when evaluated on existing datasets. The models, however, still perform far from being satisfactory when applied to real-world daily scenes. Based on our analyses, we first identify 7 crucial aspects that a comprehensive and balanced dataset should fulfill. Then, we propose a new high quality dataset and update the previous saliency benchmark. Specifically, our SOC (Salient Objects in Clutter) dataset, includes images with salient and non-salient objects from daily object categories. Beyond object category annotations, each salient image is accompanied by attributes that reflect common challenges in real-world scenes. Finally, we report attribute-based performance assessment on our dataset.
Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground
Deng-Ping Fan,Jiangjiang Liu,Shanghua Gao,Qibin Hou,A. Borji,Ming-Ming Cheng
Published 2018 in European Conference on Computer Vision
ABSTRACT
PUBLICATION RECORD
- Publication year
2018
- Venue
European Conference on Computer Vision
- Publication date
2018-03-16
- Fields of study
Computer Science
- Identifiers
- External record
- Source metadata
Semantic Scholar
CITATION MAP
EXTRACTION MAP
CLAIMS
- No claims are published for this paper.
CONCEPTS
- No concepts are published for this paper.
REFERENCES
Showing 1-50 of 50 references · Page 1 of 1