Xibing Zuo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xibing Zuo has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
Bing Liu
5 shared publications- Anzhu Yu
Information Engineering University, Zhengzhou, China
4 shared publications - Fei Jin
Information Engineering University, Zhengzhou, China
4 shared publications - Xiao Liu
Information Engineering University, Zhengzhou, China
4 shared publications - Yuzhun Lin
Information Engineering University, Zhengzhou, China
4 shared publications - Bing Liu
Information Engineering University, Zhengzhou, China
3 shared publications
Latest Publications
- 4 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-17
Integrating Segment Anything Model With Instance-Level Change Generation for Single-Temporal Unsupervised Change Detection
Implementing change detection (CD) with bi-temporal remote sensing images (RSIs) is essential for gaining insights into the dynamic evolution of the Earth’s surface. Recent advancements in deep learning methodologies have demonstrated considerable success in CD applications. However, the efficacy of supervised CD networks is significantly constrained by their dependence on high-quality change labels and precisely registered bi-temporal RSIs, which imposes significant limitations in real-world scenarios. To address this issue, we propose a novel single-temporal unsupervised CD method, STU-SAMI, which integrates the Segment Anything Model (SAM) with instance-level change generation. This method aims to facilitate the training of high-performance CD networks using unpaired and unlabeled single-temporal RSIs. The proposed approach comprises three main steps. First, the SAM is introduced to extract morphologically complete object instances from single-temporal RSIs. Second, an online instance-level change generation method is proposed, which transforms single-temporal RSIs into bi-temporal pseudo change samples based on the object instances obtained by SAM. Third, a streamlined and efficient deep Siamese CD network is constructed to support the training and inference processes. Extensive experiments conducted on three benchmark datasets demonstrate that the proposed method outperforms the existing state-of-the-art unsupervised CD methods. The code is available at https://github.com/IceStreams/STU-SAMI.
- 4 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-17
Integrating Segment Anything Model With Instance-Level Change Generation for Single-Temporal Unsupervised Change Detection
Implementing change detection (CD) with bi-temporal remote sensing images (RSIs) is essential for gaining insights into the dynamic evolution of the Earth’s surface. Recent advancements in deep learning methodologies have demonstrated considerable success in CD applications. However, the efficacy of supervised CD networks is significantly constrained by their dependence on high-quality change labels and precisely registered bi-temporal RSIs, which imposes significant limitations in real-world scenarios. To address this issue, we propose a novel single-temporal unsupervised CD method, STU-SAMI, which integrates the Segment Anything Model (SAM) with instance-level change generation. This method aims to facilitate the training of high-performance CD networks using unpaired and unlabeled single-temporal RSIs. The proposed approach comprises three main steps. First, the SAM is introduced to extract morphologically complete object instances from single-temporal RSIs. Second, an online instance-level change generation method is proposed, which transforms single-temporal RSIs into bi-temporal pseudo change samples based on the object instances obtained by SAM. Third, a streamlined and efficient deep Siamese CD network is constructed to support the training and inference processes. Extensive experiments conducted on three benchmark datasets demonstrate that the proposed method outperforms the existing state-of-the-art unsupervised CD methods. The code is available at https://github.com/IceStreams/STU-SAMI.
- Open Access
- 18 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18  (19391404) , 9723-9737
Joint Spectral Information and Spatial Details for Road Extraction From Optical Remote-Sensing Images
Currently, satellite remote sensing image acquisition systems typically include two forms of panchromatic and multispectral images, both of which have complementary advantages in spatial and channel dimensions. However, translating advantageous information into a deciphering function in road extraction tasks remains a challenge. This study, therefore, proposes a road-extraction method combining spectral information and spatial details. First, a multibranch network framework was built based on an encoding-decoding structure. The encoding layers of the panchromatic and multispectral image branches were constructed from the residual modules. Fusion branches were then constructed during the decoding phase. The spectral information of the multispectral image and spatial details of the panchromatic image were then obtained using the HIS color transform and Haar wavelet transform, respectively, and injected into the fusion branch. A polarized self-attention mechanism was finally introduced at different levels of the fusion branch to reduce information loss during feature extraction, and operations such as connected convolution and nonlinear activation were later connected to complete the road prediction. The implementation of the proposed method on the GF2-FC and CHN6-CUG datasets revealed a superior performance compared to comparative methods in terms of quantitative evaluation metrics. The proposed method performed the strongest in several scenarios, particularly in difficult road extraction areas such as shadows and vegetation cover.
- 18 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18  (19391404) , 9723-9737
Open AccessJoint Spectral Information and Spatial Details for Road Extraction From Optical Remote-Sensing Images
Currently, satellite remote sensing image acquisition systems typically include two forms of panchromatic and multispectral images, both of which have complementary advantages in spatial and channel dimensions. However, translating advantageous information into a deciphering function in road extraction tasks remains a challenge. This study, therefore, proposes a road-extraction method combining spectral information and spatial details. First, a multibranch network framework was built based on an encoding-decoding structure. The encoding layers of the panchromatic and multispectral image branches were constructed from the residual modules. Fusion branches were then constructed during the decoding phase. The spectral information of the multispectral image and spatial details of the panchromatic image were then obtained using the HIS color transform and Haar wavelet transform, respectively, and injected into the fusion branch. A polarized self-attention mechanism was finally introduced at different levels of the fusion branch to reduce information loss during feature extraction, and operations such as connected convolution and nonlinear activation were later connected to complete the road prediction. The implementation of the proposed method on the GF2-FC and CHN6-CUG datasets revealed a superior performance compared to comparative methods in terms of quantitative evaluation metrics. The proposed method performed the strongest in several scenarios, particularly in difficult road extraction areas such as shadows and vegetation cover.
- Open Access
- 28 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18  (19391404) , 61-77
Multitask Siamese Network Guided by Enhanced Change Information for Semantic Change Detection in Bitemporal Remote Sensing Images
Semantic change detection (SCD) represents a challenging task in the interpretation of remote sensing images (RSIs), with the goal of identifying change regions and extracting semantic information from bitemporal RSIs simultaneously. The recent integration of deep neural networks leveraging multitask learning has shown promise in enhancing SCD performance. However, there is still a challenge in improving SCD performance, specifically in designing a fine-grained network structure that can handle the two subtasks of change region localization and semantic information recognition in parallel. In this context, a novel multitask Siamese network, termed EGMS-Net, is proposed to boost the performance of SCD, which consists of three core components. First, a coarse-to-fine multitask Siamese network is constructed to obtain semantic information and change information at multiple levels. Second, an adaptive change information enhancement method based on spatial-spectral collaborative attention mechanism is proposed, which can assist the accurate localization of change regions without significantly increasing the model parameters. Third, a change information guidance module is developed to strengthen the interaction between multitask branches and reduce the difficulty of network training. Experiments on three benchmark datasets demonstrate that the proposed EGMS-Net outperforms existing state-of-the-art methods in the SCD community.
- 28 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18  (19391404) , 61-77
Open AccessMultitask Siamese Network Guided by Enhanced Change Information for Semantic Change Detection in Bitemporal Remote Sensing Images
Semantic change detection (SCD) represents a challenging task in the interpretation of remote sensing images (RSIs), with the goal of identifying change regions and extracting semantic information from bitemporal RSIs simultaneously. The recent integration of deep neural networks leveraging multitask learning has shown promise in enhancing SCD performance. However, there is still a challenge in improving SCD performance, specifically in designing a fine-grained network structure that can handle the two subtasks of change region localization and semantic information recognition in parallel. In this context, a novel multitask Siamese network, termed EGMS-Net, is proposed to boost the performance of SCD, which consists of three core components. First, a coarse-to-fine multitask Siamese network is constructed to obtain semantic information and change information at multiple levels. Second, an adaptive change information enhancement method based on spatial-spectral collaborative attention mechanism is proposed, which can assist the accurate localization of change regions without significantly increasing the model parameters. Third, a change information guidance module is developed to strengthen the interaction between multitask branches and reduce the difficulty of network training. Experiments on three benchmark datasets demonstrate that the proposed EGMS-Net outperforms existing state-of-the-art methods in the SCD community.
- Open Access
- 9 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Multi-task Siamese Network Guided by Enhanced Change Information for Semantic Change Detection in Bi-Temporal Remote Sensing Images
Semantic change detection (SCD) represents a challenging task in the interpretation of remote sensing images (RSIs), with the goal of identifying change regions and extracting semantic information from bi-temporal RSIs simultaneously. The recent integration of deep neural networks leveraging multi-task learning has shown promise in enhancing SCD performance. However, there is still a challenge in improving SCD performance, specifically in designing a fine-grained network structure that can handle the two subtasks of change region localization and semantic information recognition in parallel. In this context, a novel multi-task Siamese network, termed EGMS-Net, is proposed to boost the performance of SCD, which consists of three core components. Firstly, a coarse-to-fine multi-task Siamese network is constructed to obtain semantic information and change information at multiple levels. Secondly, an adaptive change information enhancement method based on spatialspectral collaborative attention mechanism is proposed, which can assist the accurate localization of change regions without significantly increasing the model parameters. Thirdly, a change information guidance module is developed to strengthen the interaction between multi-task branches and reduce the difficulty of network training. Experiments on two benchmark datasets demonstrate that the proposed EGMS-Net outperforms existing state-of-the-art methods in the SCD community. The code of this work will be available at https://github.com/IceStreams/EGMS-Net.
- 9 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessMulti-task Siamese Network Guided by Enhanced Change Information for Semantic Change Detection in Bi-Temporal Remote Sensing Images
Semantic change detection (SCD) represents a challenging task in the interpretation of remote sensing images (RSIs), with the goal of identifying change regions and extracting semantic information from bi-temporal RSIs simultaneously. The recent integration of deep neural networks leveraging multi-task learning has shown promise in enhancing SCD performance. However, there is still a challenge in improving SCD performance, specifically in designing a fine-grained network structure that can handle the two subtasks of change region localization and semantic information recognition in parallel. In this context, a novel multi-task Siamese network, termed EGMS-Net, is proposed to boost the performance of SCD, which consists of three core components. Firstly, a coarse-to-fine multi-task Siamese network is constructed to obtain semantic information and change information at multiple levels. Secondly, an adaptive change information enhancement method based on spatialspectral collaborative attention mechanism is proposed, which can assist the accurate localization of change regions without significantly increasing the model parameters. Thirdly, a change information guidance module is developed to strengthen the interaction between multi-task branches and reduce the difficulty of network training. Experiments on two benchmark datasets demonstrate that the proposed EGMS-Net outperforms existing state-of-the-art methods in the SCD community. The code of this work will be available at https://github.com/IceStreams/EGMS-Net.
- 3 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21  (1545598X) , 1-5
Attention Prompt-Driven Source-Free Adaptation for Remote Sensing Images Semantic Segmentation
Recently, remote sensing images (RSIs) domain adaptation segmentation has been extensively studied. However, existing methods generally assume that source RSIs must be available, which is obviously an overly demanding condition and will increase unnecessary costs in practice. To this end, this paper takes the lead in exploring RSIs source-free adaptation segmentation, where only the offline model pretrained on the source domain and target RSIs are available. A novel method featuring prompt learning and vision foundation models is proposed, and the novelty design includes two aspects. Firstly, to better adapt the general-purpose knowledge in the foundation model to different target RSIs, an attention-guided prompt tuning strategy is proposed, which can dynamically steer the knowledge at different layers and positions through prompts with different weights. Secondly, a feature alignment strategy with similarity distance is proposed for source-free domain adaptation by taking full advantage of the representation ability of the foundation model and the flexibility of prompt learning. Extensive experiments indicate that the performance of the proposed method is significantly superior to that of existing methods. Specifically, the mIoU of target RSIs has been improved by at least 3.14%~4.18%.
- 3 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21  (1545598X) , 1-5
Attention Prompt-Driven Source-Free Adaptation for Remote Sensing Images Semantic Segmentation
Recently, remote sensing images (RSIs) domain adaptation segmentation has been extensively studied. However, existing methods generally assume that source RSIs must be available, which is obviously an overly demanding condition and will increase unnecessary costs in practice. To this end, this paper takes the lead in exploring RSIs source-free adaptation segmentation, where only the offline model pretrained on the source domain and target RSIs are available. A novel method featuring prompt learning and vision foundation models is proposed, and the novelty design includes two aspects. Firstly, to better adapt the general-purpose knowledge in the foundation model to different target RSIs, an attention-guided prompt tuning strategy is proposed, which can dynamically steer the knowledge at different layers and positions through prompts with different weights. Secondly, a feature alignment strategy with similarity distance is proposed for source-free domain adaptation by taking full advantage of the representation ability of the foundation model and the flexibility of prompt learning. Extensive experiments indicate that the performance of the proposed method is significantly superior to that of existing methods. Specifically, the mIoU of target RSIs has been improved by at least 3.14%~4.18%.
- 16 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62  (01962892) , 1-17
Multimodal Online Knowledge Distillation Framework for Land Use/Cover Classification Using Full or Missing Modalities
Multimodal land use/cover classification using optical and synthetic aperture radar (SAR) images has attracted significant attention because the unique radiation and geometric characteristics of these images provide complementary information regarding land properties. However, the significant differences between these modalities create a large semantic gap, posing challenges for effective feature fusion in multimodal learning. Moreover, missing modalities often occur in practical applications due to weather constraints or sensor malfunctions, posing challenges to achieving high performance in cross-modal learning. In this study, we proposed a multimodal online knowledge distillation (MMOKD) framework, designed for land use/cover classification of optical and SAR images using either full or missing modalities. This framework trains one modality-fusion network alongside two modality-specific networks in an end-to-end manner, facilitating both multimodal and cross-modal learning. More specifically, we developed a multimodal feature fusion (MFF) module for integrating heterogeneous features and a single-modal feature generation (SFG) module for encapsulating cross-modal complementary information. In addition, we proposed the joint distillation with multitype fusion knowledge (JD-MFK) method, guiding the modality-specific student networks to comprehensively learn the modality-fusion teacher network. Notably, we adopted an online distillation strategy for real-time feedback and synchronous updates of both modality-fusion and modality-specific networks. Finally, we conducted extensive experiments on two multimodal land use/classification datasets with advanced multimodal fusion, cross-modal distillation, and specific baseline networks for comparison. The results demonstrate the effectiveness of the proposed MMODD, which not only outperforms the other networks in both full- and missing-modality scenarios but also significantly improves model training efficiency.
- 16 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62  (01962892) , 1-17
Multimodal Online Knowledge Distillation Framework for Land Use/Cover Classification Using Full or Missing Modalities
Multimodal land use/cover classification using optical and synthetic aperture radar (SAR) images has attracted significant attention because the unique radiation and geometric characteristics of these images provide complementary information regarding land properties. However, the significant differences between these modalities create a large semantic gap, posing challenges for effective feature fusion in multimodal learning. Moreover, missing modalities often occur in practical applications due to weather constraints or sensor malfunctions, posing challenges to achieving high performance in cross-modal learning. In this study, we proposed a multimodal online knowledge distillation (MMOKD) framework, designed for land use/cover classification of optical and SAR images using either full or missing modalities. This framework trains one modality-fusion network alongside two modality-specific networks in an end-to-end manner, facilitating both multimodal and cross-modal learning. More specifically, we developed a multimodal feature fusion (MFF) module for integrating heterogeneous features and a single-modal feature generation (SFG) module for encapsulating cross-modal complementary information. In addition, we proposed the joint distillation with multitype fusion knowledge (JD-MFK) method, guiding the modality-specific student networks to comprehensively learn the modality-fusion teacher network. Notably, we adopted an online distillation strategy for real-time feedback and synchronous updates of both modality-fusion and modality-specific networks. Finally, we conducted extensive experiments on two multimodal land use/classification datasets with advanced multimodal fusion, cross-modal distillation, and specific baseline networks for comparison. The results demonstrate the effectiveness of the proposed MMODD, which not only outperforms the other networks in both full- and missing-modality scenarios but also significantly improves model training efficiency.
- Open Access
- 27 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17  (19391404) , 3236-3250
Joint Network Combining Dual-Attention Fusion Modality and Two Specific Modalities for Land Cover Classification Using Optical and SAR Images
Optical and Synthetic Aperture Radar (SAR) images provide various complementary information on land properties, which can substantially improve the accuracy of land cover classification because of the fusion of their multi-source information. However, excellent extraction of the discriminative information of Optical and SAR images and effective integration of the interpretation information of multi-source data remain challenging issues. In this study, we have proposed a novel joint network that combines a dual-attention fusion modality and two specific modalities to achieve superior land cover classification maps, which has two modes of encoding-level fusion (JoiTriNet-e) and decoding-level fusion (JoiTriNet-d). We first proposed a strategy for the fusion modality and specific modalities joint learning, the goal of which was to simultaneously find three mapping functions that project optical and SAR images separately and together into semantic maps. Two architectures were constructed using the proposed strategy, which improved the performance of multi-source and single-source land cover classification. To aggregate the heterogeneous features of optical and SAR images more reasonably, we designed a multimodal dual-attention fusion module. Experiments were conducted on two multi-source land cover datasets, among which comparison experiments highlighted the superiority and robustness of our model, and ablation experiments verified the effectiveness of the proposed architecture and module.
- 27 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17  (19391404) , 3236-3250
Open AccessJoint Network Combining Dual-Attention Fusion Modality and Two Specific Modalities for Land Cover Classification Using Optical and SAR Images
Optical and Synthetic Aperture Radar (SAR) images provide various complementary information on land properties, which can substantially improve the accuracy of land cover classification because of the fusion of their multi-source information. However, excellent extraction of the discriminative information of Optical and SAR images and effective integration of the interpretation information of multi-source data remain challenging issues. In this study, we have proposed a novel joint network that combines a dual-attention fusion modality and two specific modalities to achieve superior land cover classification maps, which has two modes of encoding-level fusion (JoiTriNet-e) and decoding-level fusion (JoiTriNet-d). We first proposed a strategy for the fusion modality and specific modalities joint learning, the goal of which was to simultaneously find three mapping functions that project optical and SAR images separately and together into semantic maps. Two architectures were constructed using the proposed strategy, which improved the performance of multi-source and single-source land cover classification. To aggregate the heterogeneous features of optical and SAR images more reasonably, we designed a multimodal dual-attention fusion module. Experiments were conducted on two multi-source land cover datasets, among which comparison experiments highlighted the superiority and robustness of our model, and ablation experiments verified the effectiveness of the proposed architecture and module.
- 12 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32  (10577149) , 5181-5196
Hyperspectral Meets Optical Flow: Spectral Flow Extraction for Hyperspectral Image Classification
Hyperspectral image (HSI) classification has always been recognised as a difficult task. It is therefore a research hotspot in remote sensing image processing and analysis, and a number of studies have been conducted to better extract spectral and spatial features. This study aimed to track the variation of the spectrum in hyperspectral images from a sequential data perspective to obtain more distinguishable features. Based on the characteristics of optical flow, this study introduces an optical flow technique for the extraction of spectral flow that denotes the spectral variation and implements a dense optical flow extraction method based on deep matching. Lastly, the extracted spectral flow are combined with the original spectral features and input into a commonly used support vector machine (SVM) classifier to complete the classification. Extensive classification experiments on three benchmark HSI test sets show that the classification accuracy obtained by the spectral flow extracted in this study (SpectralFlow) is higher than traditional spatial feature extraction methods, texture feature extraction methods, and the latest deep-learning-based methods. Furthermore, the proposed method can produce finer classification thematic maps, thereby demonstrating strong practical application potential.
- 12 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32  (10577149) , 5181-5196
Hyperspectral Meets Optical Flow: Spectral Flow Extraction for Hyperspectral Image Classification
Hyperspectral image (HSI) classification has always been recognised as a difficult task. It is therefore a research hotspot in remote sensing image processing and analysis, and a number of studies have been conducted to better extract spectral and spatial features. This study aimed to track the variation of the spectrum in hyperspectral images from a sequential data perspective to obtain more distinguishable features. Based on the characteristics of optical flow, this study introduces an optical flow technique for the extraction of spectral flow that denotes the spectral variation and implements a dense optical flow extraction method based on deep matching. Lastly, the extracted spectral flow are combined with the original spectral features and input into a commonly used support vector machine (SVM) classifier to complete the classification. Extensive classification experiments on three benchmark HSI test sets show that the classification accuracy obtained by the spectral flow extracted in this study (SpectralFlow) is higher than traditional spatial feature extraction methods, texture feature extraction methods, and the latest deep-learning-based methods. Furthermore, the proposed method can produce finer classification thematic maps, thereby demonstrating strong practical application potential.
- 4 May 2023
- Published by Taylor & Francis in Remote Sensing Letters
- Vol. 14  (5) , 479-490
Semi-supervised classification of hyperspectral images based on multi-view consistency
- 4 May 2023
- Published by Taylor & Francis in Remote Sensing Letters
- Vol. 14  (5) , 479-490
Semi-supervised classification of hyperspectral images based on multi-view consistency
- Open Access
- 6 April 2023
- Published by Taylor & Francis in European Journal of Remote Sensing
- Vol. 56  (1)
Deep hierarchical transformer for change detection in high-resolution remote sensing images
Deep learning instantiated by convolutional neural networks has achieved great success in high-resolution remote-sensing image change detection. However, such networks have a limited receptive field, being unable to extract long-range dependencies in a scene. As the transformer model with self-attention can better describe long-range dependencies, we introduce a hierarchical transformer model to improve the precision of change detection in high-resolution remote sensing images. First, the hierarchical transformer extracts abstract features from multitemporal remote sensing images. To effectively minimize the model’s complexity and enhance the feature representation, we limit the self-attention calculation of each transformer layer to local windows with different sizes. Then, we combine the features extracted by the hierarchical transformer and input them into a nested U-Net to obtain the change detection results. Furthermore, a simple but effective model fusion strategy is adopted to improve the change detection accuracy. Extensive experiments are carried out on two large-scale data sets for change detection, LEVIR-CD and SYSU-CD. The quantitative and qualitative experimental results suggest that the proposed method outperforms the advanced methods in terms of detection performance.
- 6 April 2023
- Published by Taylor & Francis in European Journal of Remote Sensing
- Vol. 56  (1)
Open AccessDeep hierarchical transformer for change detection in high-resolution remote sensing images
Deep learning instantiated by convolutional neural networks has achieved great success in high-resolution remote-sensing image change detection. However, such networks have a limited receptive field, being unable to extract long-range dependencies in a scene. As the transformer model with self-attention can better describe long-range dependencies, we introduce a hierarchical transformer model to improve the precision of change detection in high-resolution remote sensing images. First, the hierarchical transformer extracts abstract features from multitemporal remote sensing images. To effectively minimize the model’s complexity and enhance the feature representation, we limit the self-attention calculation of each transformer layer to local windows with different sizes. Then, we combine the features extracted by the hierarchical transformer and input them into a nested U-Net to obtain the change detection results. Furthermore, a simple but effective model fusion strategy is adopted to improve the change detection accuracy. Extensive experiments are carried out on two large-scale data sets for change detection, LEVIR-CD and SYSU-CD. The quantitative and qualitative experimental results suggest that the proposed method outperforms the advanced methods in terms of detection performance.