arrow
返回

Dynamic attention network for semantic segmentation

delete2020-04-01
delete34
PRE
AI
F
Fei Wu *
F
Feng Chen
X
Xiao‐Yuan Jing
C
Changhui Hu
Q
Qi Ge
Y
Yimu Ji
DOI:10.1016/j.neucom.2019.12.042delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Semantic segmentation networks usually utilize special pyramid structure after encoder or combine low-level and high-level feature maps in decoder to capture multi-scale context information, which we term them feature combination and feature connection, respectively. However, both such frameworks are less valid with the fixed geometric structure or unsuitable interim. In this paper, we advocate Dynamic Attention Network (DAN) to solve these problems. First, we design a Deformable Attention Pyramid (DAP) module to perform a self-adjustable descriptor of high-level output, which utilizes deformable function to model geometric transformation. With DAP, semantic information can be captured effectively. Second, we propose a Fusing Attention Interim (FAI) module to guide the back-propagation of long-short range information in each level of decoder. We evaluate DAN on the challenging PASCAL VOC 2012 and Cityscapes segmentation benchmarks and find that it achieves state-of-the-art results without post-processing. Our observation can be concluded that the flexible structure that possesses dynamic attention mechanism is beneficial to learn multi-scale context information. (C) 2019 Elsevier B.V. All rights reserved.
Keyword:
Semantic segmentation
Deformable convolution
Geometric transformation
Attention mechanism
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Neurocomputing 封面图
Neurocomputing
IF:
6.5
论文数:
2.5W
被引数:
6.5W

机构

暂无机构信息
引用论文

引用论文

Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THV
err2015-01-01
err0
PREAI
errC. Perréard; Y. Ladner; F. d'Orlyé; S. Descroix; V. Taniga; A. Varenne; F. Kanoufi; C. Slim; S. Griveau; F. Bedioui
err分享
err收藏
The Pascal Visual Object Classes (VOC) ChallengePascal视觉对象课程 (VOC) 挑战
err2009-09-09
err9.0K
PREAI
errEveringham, Mark; Van Gool, Luc; Williams, Christopher K. I.; Winn, John; Zisserman, Andrew
err分享
err收藏
没有更多内容