.png){kind=icon}
返回
BINet: Bidirectional interactive network for salient object detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2021.09.020.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Existing state-of-the-art methods for salient object detection mainly achieve significant progress by inte-grating multi-level features. However, most of them simply resize the multi-level features to the same spatial resolution and aggregate them by channel-wise concatenation or element-wise addition. Thus, they are limited to integrating features of adjacent layers due to large discrepancy between these multi-level features. Besides, most existing methods adopt the U-shape architecture where high-level semantic information is gradually transmitted to shallower layers to suppress the background noises. Nonetheless, little attention has been paid to refine high-level features. In this paper, we propose the BINet to solve the above problems. Specifically, we design the feature interaction module (FIM) to exploit complementary information between multiple features, which is then utilized to simultaneously refine these features. Besides, we propose the cascaded bidirectional interaction decoder (CBID) to further refine multi-level features iteratively. Our CBID progressively refines multi-level features with feedback mech-anisms and employs a channel attention module (CAM) to assign larger weights to channels showing higher response to salient regions. Equipped with these modules, our BINet is capable of segmenting sali-ent regions accurately and quickly. Experimental results on six widely used benchmark datasets validate that our BINet outperforms 16 other state-of-the-art methods in terms of 7 standard evaluation metrics. Our code will be publicly available at https://github.com/clelouch/BINet. (c) 2021 Elsevier B.V. All rights reserved.
Keyword:
Channel attention
Deep learning
Feedback mechanisms
Multi-level feature integration
Salient object detection
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
.png){kind=icon}
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
分享收藏分享收藏
分享收藏
查看更多内容