Saliency Detection by Multi-Context Deep Learning
文献类型：会议论文
| 作者 | Rui Zhao; Wanli Ouyang; Hongsheng Li; Xiaogang Wang |
| 出版日期 | 2015 |
| 会议名称 | IEEE Conference on Computer Vision and Pattern Recognition |
| 会议地点 | 美国波士顿 |
| 英文摘要 | 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. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/6701]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2015 |
| 推荐引用方式 GB/T 7714 | Rui Zhao,Wanli Ouyang,Hongsheng Li,et al. Saliency Detection by Multi-Context Deep Learning[C]. 见:IEEE Conference on Computer Vision and Pattern Recognition. 美国波士顿. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。