DAHT-Net: Deformable Attention-guided Hierarchical Transformer Network Based On Remote Sensing Image Change Detection

Remote sensing image change detection (CD) refers to the automated or semi-automated detection of differences between two remote sensing images taken at different times in the same region. To achieve better global modeling and faster inference, we propose a network architecture containing a hierarch...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2023-01, Vol.11, p.1-1
Main Authors: Shi, Gang, Mei, Yunfei, Wang, XiaoLi, Yang, QingWen
Format: Article
Language:English
Subjects:
Automation
Change detection
Change detection algorithms
Computer architecture
Convolutional neural networks
Decoding
deformable attention
Deformable models
Deformation
Feature extraction
Formability
global modeling
Globalization
Hierarchical systems
hierarchical transformer
Inference
Lightweight
Remote sensing
Task analysis
Transformers
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:Remote sensing image change detection (CD) refers to the automated or semi-automated detection of differences between two remote sensing images taken at different times in the same region. To achieve better global modeling and faster inference, we propose a network architecture containing a hierarchical swin transformer block and deformable attention transformers crossed for encoding and lightweight MLP decoding to solve the CD task. The deformable attention transformer allows adaptive adjustment of the relationships and weights between feature mappings to effectively combat variations and noise interference in various scenes. The alternating use of swin transformer block and deformable attention transformer ensures the efficiency as well as the flexibility of the model. The lightweight MLP approach provides better ability to extract spatial features and contextual information, as well as faster inference speed. Compared with other methods, our proposed DAHT-Net method improves F1 scores by 0.98 and 2.61 on LEVIR-CD, CDD and two publicly available benchmark datasets, respectively, and performs well on other measures. These experimental results validate that the DAHT-Net network outperforms other comparative methods and highlight its effectiveness in remote sensing image change detection. In summary, our proposed hierarchical deformable attention-guided transformer network model provides a promising solution for remote sensing image change detection with superior performance compared to other state-of-the-art methods.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2023.3307642