.png){kind=icon}
返回
Semantic segmentation using stride spatial pyramid pooling and dual attention decoder
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2020.107498.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Semantic segmentation is an end-to-end task that requires both semantic and spatial accuracy. It is important for deep learning-based segmentation methods to effectively utilize the high-level feature map whose semantic information is abundant and the low-level feature map whose spatial information is accurate. However, existing segmentation networks typically cannot take full advantage of these two kinds of feature maps, leading to inferior performance. This paper attempts to overcome this challenge by introducing two novel structures. On the one hand, we propose a structure called stride spatial pyramid pooling (SSPP) to capture multiscale semantic information from the high-level feature map. Compared with existing pyramid pooling methods based on the atrous convolution, the SSPP structure is able to gather more information from the high-level feature map with faster inference speed, which improves the utilization efficiency of the high-level feature map significantly. On the other hand, we propose a dual attention decoder consisting of a channel attention branch and a spatial attention branch to make full use of the high- and low-level feature maps simultaneously. The dual attention decoder can result in a more semantic low-level feature map and a high-level feature map with more accurate spatial information, which bridges the gap between these two kinds of feature maps and benefits their fusion. We evaluate the proposed model on several publicly available semantic image segmentation benchmarks including PASCAL VOC 2012, Cityscapes and COCO-Stuff. The qualitative and quantitative results demonstrate that our method can achieve the state-of-the-art performance. (C) 2020 Elsevier Ltd. All rights reserved.
Keyword:
Semantic segmentation
Convolutional neural networks
Pyramid pooling
Attention mechanism
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
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THV.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏A multi-scale level set method based on local features for segmentation of images with intensity inhomogeneityPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Active contours driven by global and local weighted signed pressure force for image segmentationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Dual-force convolutional neural networks for accurate brain tumor segmentationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Deep gated attention networks for large-scale street-level scene segmentationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容