Journal
SENSORS
Volume 20, Issue 9, Pages -Publisher
MDPI
DOI: 10.3390/s20092656
Keywords
visual saliency; multi-scale; global contrast; CNN
Funding
- NSFC (Natural Science Foundation of China) [61602345]
- National Key Research and Development Plan [2019YFB2101900]
- Application Foundation and Advanced Technology Research Project of Tianjin [15JCQNJC01400]
Ask authors/readers for more resources
Salient object detection (SOD) is a fundamental task in computer vision, which attempts to mimic human visual systems that rapidly respond to visual stimuli and locate visually salient objects in various scenes. Perceptual studies have revealed that visual contrast is the most important factor in bottom-up visual attention process. Many of the proposed models predict saliency maps based on the computation of visual contrast between salient regions and backgrounds. In this paper, we design an end-to-end multi-scale global contrast convolutional neural network (CNN) that explicitly learns hierarchical contrast information among global and local features of an image to infer its salient object regions. In contrast to many previous CNN based saliency methods that apply super-pixel segmentation to obtain homogeneous regions and then extract their CNN features before producing saliency maps region-wise, our network is pre-processing free without any additional stages, yet it predicts accurate pixel-wise saliency maps. Extensive experiments demonstrate that the proposed network generates high quality saliency maps that are comparable or even superior to those of state-of-the-art salient object detection architectures.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available