Unsupervised Domain Adaptation for Cloud Detection Based on Grouped Features Alignment and Entropy Minimization

Most convolutional neural network (CNN)-based cloud detection methods are built upon the supervised learning framework that requires a large number of pixel-level labels. However, it is expensive and time-consuming to manually annotate pixelwise labels for massive remote sensing images. To reduce th...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2022, Vol.60, p.1-13
Main Authors: Guo, Jianhua, Yang, Jingyu, Yue, Huanjing, Li, Kun
Format: Article
Language:English
Subjects:
Adaptation
Adaptation models
Alignment
Artificial neural networks
Cloud detection
Detection
Domains
Entropy
entropy minimization (EM)
Feature extraction
grouped features alignment (GFA)
Labels
Landsat
Landsat satellites
Neural networks
Optimization
Remote sensing
remote sensing (RS) imagery
Satellite imagery
Satellites
Semantics
Spaceborne remote sensing
Task analysis
Training
unsupervised domain adaptation (UDA)
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most convolutional neural network (CNN)-based cloud detection methods are built upon the supervised learning framework that requires a large number of pixel-level labels. However, it is expensive and time-consuming to manually annotate pixelwise labels for massive remote sensing images. To reduce the labeling cost, we propose an unsupervised domain adaptation (UDA) approach to generalize the model trained on labeled images of source satellite to unlabeled images of the target satellite. To effectively address the domain shift problem on cross-satellite images, we develop a novel UDA method based on grouped features alignment (GFA) and entropy minimization (EM) to extract domain-invariant representations to improve the cloud detection accuracy of cross-satellite images. The proposed UDA method is evaluated on "Landsat- 8~\rightarrow ZY-3" and "GF- 1\rightarrow ZY-3" domain adaptation tasks. Experimental results demonstrate the effectiveness of our method against existing state-of-the-art UDA approaches. The code of this paper has been made available online ( https://github.com/nkszjx/grouped-features-alignment ).
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2021.3067513