期刊
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
卷 -, 期 -, 页码 3127-3135出版社
IEEE
DOI: 10.1109/CVPR.2018.00330
关键词
-
资金
- National Natural Science Foundation of China [61371157, 61472060, 61528101]
- Fundamental Research Funds for the Central Universities [DUT2017TB04, DUT17TD03]
Effective integration of contextual information is crucial for salient object detection. To achieve this, most existing methods based on 'skip' architecture mainly focus on how to integrate hierarchical features of Convolutional Neural Networks (CNNs). They simply apply concatenation or element-wise operation to incorporate high-level semantic cues and low-level detailed information. However, this can degrade the quality of predictions because cluttered and noisy information can also be passed through. To address this problem, we proposes a global Recurrent Localization Network (RLN) which exploits contextual information by the weighted response map in order to localize salient objects more accurately. Particularly, a recurrent module is employed to progressively refine the inner structure of the CNN over multiple time steps. Moreover, to effectively recover object boundaries, we propose a local Boundary Refinement Network (BRN) to adaptively learn the local contextual information for each spatial position. The learned propagation coefficients can be used to optimally capture relations between each pixel and its neighbors. Experiments on five challenging datasets show that our approach performs favorably against all existing methods in terms of the popular evaluation metrics.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据