Title :
Saliency detection by multi-context deep learning
Author :
Rui Zhao;Wanli Ouyang;Hongsheng Li;Xiaogang Wang
Author_Institution :
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Chuangyeyuan Rd, Longgang, Guangdong, China
fDate :
6/1/2015 12:00:00 AM
Abstract :
Low-level saliency cues or priors do not produce good enough saliency detection results especially when the salient object presents in a low-contrast background with confusing visual appearance. This issue raises a serious problem for conventional approaches. In this paper, we tackle this problem by proposing a multi-context deep learning framework for salient object detection. We employ deep Convolutional Neural Networks to model saliency of objects in images. Global context and local context are both taken into account, and are jointly modeled in a unified multi-context deep learning framework. To provide a better initialization for training the deep neural networks, we investigate different pre-training strategies, and a task-specific pre-training scheme is designed to make the multi-context modeling suited for saliency detection. Furthermore, recently proposed contemporary deep models in the ImageNet Image Classification Challenge are tested, and their effectiveness in saliency detection are investigated. Our approach is extensively evaluated on five public datasets, and experimental results show significant and consistent improvements over the state-of-the-art methods.
Keywords :
"Context","Context modeling","Predictive models","Training","Visualization","Object detection","Machine learning"
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on
Electronic_ISBN :
1063-6919
DOI :
10.1109/CVPR.2015.7298731