Compact Position-Aware Attention Network for Image Semantic Segmentation

2019 ◽  
pp. 639-650
Author(s):  
Yajun Xu ◽  
Zhendong Mao ◽  
Peng Zhang ◽  
Bin Wang
Keyword(s):  
Semantic Segmentation ◽  
Attention Network

scholarly journals Hybrid Multiple Attention Network for Semantic Segmentation in Aerial Images

2021 ◽  
pp. 1-18
Author(s):  
Ruigang Niu ◽  
Xian Sun ◽  
Yu Tian ◽  
Wenhui Diao ◽  
Kaiqiang Chen ◽  
...  
Keyword(s):  
Semantic Segmentation ◽  
Aerial Images ◽  
Attention Network

Triple Attention Network for Multi-Class Semantic Segmentation in Aerial Images

2021 ◽  
Author(s):  
Yu Si ◽  
Yuxia Li ◽  
Huanping Wu ◽  
Lang Yuan ◽  
Yuzhen Li ◽  
...  
Keyword(s):  
Semantic Segmentation ◽  
Aerial Images ◽  
Attention Network

Point Set Attention Network For Semantic Segmentation

2020 ◽  
Author(s):  
Jie Jiang ◽  
Jing Liu ◽  
Jun Fu ◽  
Xinxin Zhu ◽  
Hanqing Lu
Keyword(s):  
Semantic Segmentation ◽  
Attention Network ◽  
Point Set

scholarly journals Point attention network for semantic segmentation of 3D point clouds

2020 ◽  
Vol 107 ◽  
pp. 107446 ◽  
Author(s):  
Mingtao Feng ◽  
Liang Zhang ◽  
Xuefei Lin ◽  
Syed Zulqarnain Gilani ◽  
Ajmal Mian
Keyword(s):  
Semantic Segmentation ◽  
Point Clouds ◽  
Attention Network ◽  
3D Point Clouds

Adaptive Multi-scale Dual Attention Network for Semantic Segmentation

2021 ◽  
Author(s):  
Weizhen Wang ◽  
Suyu Wang ◽  
Yue Li ◽  
Yue Li
Keyword(s):  
Semantic Segmentation ◽  
Attention Network ◽  
Multi Scale

scholarly journals River Segmentation of Remote Sensing Images Based on Composite Attention Network

Complexity ◽  
2022 ◽  
Vol 2022 ◽  
pp. 1-13
Author(s):  
Zhiyong Fan ◽  
Jianmin Hou ◽  
Qiang Zang ◽  
Yunjie Chen ◽  
Fei Yan
Keyword(s):  
Remote Sensing ◽  
Semantic Segmentation ◽  
Cross Entropy ◽  
Important Research ◽  
Dice Coefficient ◽  
Remote Sensing Images ◽  
Training Process ◽  
Attention Network ◽  
Evaluation Indexes ◽  
Agricultural Planning

River segmentation of remote sensing images is of important research significance and application value for environmental monitoring, disaster warning, and agricultural planning in an area. In this study, we propose a river segmentation model in remote sensing images based on composite attention network to solve the problems of abundant river details in images and the interference of non-river information including bridges, shadows, and roads. To improve the segmentation efficiency, a composite attention mechanism is firstly introduced in the central region of the network to obtain the global feature dependence of river information. Next, in this study, we dynamically combine binary cross-entropy loss that is designed for pixel-wise segmentation and the Dice coefficient loss that measures the similarity of two segmentation objects into a weighted one to optimize the training process of the proposed segmentation network. The experimental results show that compared with other semantic segmentation networks, the evaluation indexes of the proposed method are higher than those of others, and the river segmentation effect of CoANet model is significantly improved. This method can segment rivers in remote sensing images more accurately and coherently, which can meet the needs of subsequent research.

FPANet: Feature-enhanced position attention network for semantic segmentation

2021 ◽  
Vol 32 (6) ◽  
Author(s):  
Haixia Xu ◽  
Shuailong Wang ◽  
Yunjia Huang ◽  
Wei Zhou ◽  
Qi Chen ◽  
...  
Keyword(s):  
Semantic Segmentation ◽  
Attention Network

PTANet: Triple Attention Network for point cloud semantic segmentation

2021 ◽  
Vol 102 ◽  
pp. 104239
Author(s):  
Haozhe Cheng ◽  
Jian Lu ◽  
Maoxin Luo ◽  
Wei Liu ◽  
Kaibing Zhang
Keyword(s):  
Point Cloud ◽  
Semantic Segmentation ◽  
Attention Network
Sign in / Sign up

Export Citation Format

Share Document