Boundary-Aware Multitask Learning for Remote Sensing Imagery

Boundary-Aware Multitask Learning for Remote Sensing Imagery

Semantic segmentation and height estimation play fundamental roles in the scene understanding of remote sensing images with their wide variety of aerial applications. Recently, deep convolutional neural networks (DCNNs) have achieved state-of-the-art performance in both tasks. However, DCNN-based me...

Full description

Bibliographic Details
Main Authors: Yufeng Wang, Wenrui Ding, Ruiqian Zhang, Hongguang Li
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Boundary regularization (BR)
convolutional neural network (CNN)
height estimation
multitask learning (MTL)
remote sensing imagery (RSI)
scene understanding
Online Access:https://ieeexplore.ieee.org/document/9288901/

Internet

https://ieeexplore.ieee.org/document/9288901/

Similar Items