Accurate Instance Segmentation for Remote Sensing Images via Adaptive and Dynamic Feature Learning

Accurate Instance Segmentation for Remote Sensing Images via Adaptive and Dynamic Feature Learning

Instance segmentation for high-resolution remote sensing images (HRSIs) is a fundamental yet challenging task in earth observation, which aims at achieving instance-level location and pixel-level classification for instances of interest on the earth’s surface. The main difficulties come from the hug...

Full description

Bibliographic Details
Main Authors: Feng Yang, Xiangyue Yuan, Jie Ran, Wenqiang Shu, Yue Zhao, Anyong Qin, Chenqiang Gao
Format: Article
Language:English
Published: MDPI AG 2021-11-01
Series:Remote Sensing
Subjects:
remote sensing images
instance segmentation
object detection
multi-scale fusion
context attention
sample selection
Online Access:https://www.mdpi.com/2072-4292/13/23/4774

Internet

https://www.mdpi.com/2072-4292/13/23/4774

Similar Items