Global Context Encoding For Salient Objects Detection
2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)(2018)
摘要
Deep convolutional neural networks (CNNs) have gained their reputation for the success in various tasks in computer vision, including salient objects detection. However, it remains a challenge that the CNNs have repeated downsample operators and always create low-resolution predictions, which tend to loss details and finer structure of images. To detect and segment the salient objects well, it is also necessary to merge high-level semantic information and low-level fine details simultaneously. Thus, we propose a novel network structure with stage-wise refinement sub-structures. In addition, we exploit the essence of salient objects detection by encoding the global image context in a specifically designed module, which is applied to every stage of the refinement structure. So the coarse saliency map generated from the base CNN can be refined with low-level feature and global context information step-by-step. Experimental results have demonstrated that the proposed method outperforms the state-of-the-art approaches on four benchmark datasets.
更多查看译文
关键词
global context encoding,salient objects detection,convolutional neural networks,low-resolution predictions,high-level semantic information,low-level fine details,network structure,stage-wise refinement sub-structures,global image context,refinement structure,low-level feature,CNN
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要