Cloudformer: A Cloud-Removal Network Combining Self-Attention Mechanism and Convolution

Optical remote-sensing images have a wide range of applications, but they are often obscured by clouds, which affects subsequent analysis. Therefore, cloud removal becomes a necessary preprocessing step. In this paper, a novel and superior transformer-based network is proposed, named Cloudformer. Th...

Full description

Saved in:
Bibliographic Details
Published inRemote sensing (Basel, Switzerland) Vol. 14; no. 23; p. 6132
Main Authors Wu, Peiyang, Pan, Zongxu, Tang, Hairong, Hu, Yuxin
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.12.2022
Subjects
Ablation
cloud removal
Clouds
Convolution
Datasets
Deep learning
Feature extraction
Information processing
Neural networks
Remote sensing
self-attention
Teaching methods
transformer
Online AccessGet full text

Cover

More Information
Summary:Optical remote-sensing images have a wide range of applications, but they are often obscured by clouds, which affects subsequent analysis. Therefore, cloud removal becomes a necessary preprocessing step. In this paper, a novel and superior transformer-based network is proposed, named Cloudformer. The proposed method novelly combines the advantages of convolution and a self-attention mechanism: it uses convolution layers to extract simple features over a small range in the shallow layer, and exerts the advantage of a self-attention mechanism in extracting correlation in a large range in the deep layer. This method also introduces Locally-enhanced Positional Encoding (LePE) to flexibly generate suitable positional encodings for different inputs and to utilize local information to enhance encoding capabilities. Exhaustive experiments on public datasets demonstrate the superior ability of the method to remove both thin and thick clouds, and the effectiveness of the proposed modules is validated by ablation studies.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs14236132