An Adaptive Multiscale Fusion Network Based on Regional Attention for Remote Sensing Images

An Adaptive Multiscale Fusion Network Based on Regional Attention for Remote Sensing Images

With the widespread application of semantic segmentation in remote sensing images with high-resolution, how to improve the accuracy of segmentation becomes a research goal in the remote sensing field. An innovative Fully Convolutional Network (FCN) is proposed based on regional attention for improvi...

Full description

Bibliographic Details
Main Authors: Wanzhen Lu, Longxue Liang, Xiaosuo Wu, Xiaoyu Wang, Jiali Cai
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Remote sensing
fully convolutional networks
semantic segmentation
encoder-decoder architecture
regional attention
Potsdam dataset
Online Access:https://ieeexplore.ieee.org/document/9109552/

Internet

https://ieeexplore.ieee.org/document/9109552/

Similar Items