.png){kind=icon}
返回
Split-guidance network for salient object detection
.png){kind=icon}
PRE
AI
DOI：10.1007/s00371-022-02421-5.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Due to the large-scale variation in objects in practical scenes, multi-scale representation is of critical importance for salient object detection (SOD). Recent advances in multi-level feature fusion also demonstrate its contribution in consistent performance gains. Different from the existing layer-wise methods, we propose a simple yet efficient split-guidance convolution block to improve the multi-scale representation ability at a granular level in this paper. Specifically, the input feature is first split into different subsets; each of them is guided by all the subsets in front of it, in this way to increase the range of receptive fields for each network layer. By embedding it into each side-output stage of the encoder, we build a unified decoder for both RGB SOD and RGB-D SOD. Experimental results on five RGB datasets, five RGB-D datasets and three RGB-T datasets demonstrate that the proposed method without any attention mechanisms and other complex designs performs favorably against state-of-the-art approaches and also shows advantages in simplicity, efficiency and compactness.
Keyword:
Salient object detection
Split-guidance convolution
Unified decoder
期刊
IF:
2.9
论文数:
4.6K
被引数:
6.5K
机构
引用论文
LID, LEED, and Alternative Rating Systems—Integrating Low Impact Development Techniques with Green Building DesignLID，LEED和替代评级系统-将低影响开发技术与绿色建筑设计相结合
PREAI
分享收藏Urban Green Space and the Pursuit of Health Equity in Parts of the United States美国部分地区的城市绿地与对健康公平的追求
OAAI
OAAI分享收藏Innovation, creativity and governance: Social dynamics of economic performance in city-regions.png)
Innovation
InnovationIF0
PREAI
分享收藏Measuring the impact of outdated channel state information in interference alignment techniques
PREAI
分享收藏
查看更多内容