Honghao Chang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Honghao Chang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Haixia Bi
School of Information and Communications Engineering, Xian Jiaotong University, Xian, China
4 shared publications - Fan Li
Xi’an Jiaotong University
3 shared publications Chen Xu
Department of Mathematics and Fundamental Research, Peng Cheng Laboratory, Shenzhen, China
2 shared publications- Danfeng Hong
Southeast University
2 shared publications - Haoyu Wang
Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, Shanxi, China
1 shared publication - Jian Sun
Xi’an Jiaotong University
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1380-1389
Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1380-1389
Open AccessEnhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration
- Top Cited Papers
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 6081-6094
LSFMamba: Local-Enhanced Spiral Fusion Mamba for Multi-Modal Land Cover Classification
Multi-modal learning, which fuses complementary information from different modalities, has significantly improved the accuracy of land cover classification, especially under adverse conditions like cloudy or rainy weather. Recent advancements in multi-modal remote sensing land cover classification (MMRLC) have witnessed the efficacy of approaches based on CNN and Transformer. However, CNN exhibits limitations in capturing long-range dependencies, whereas Transformer suffers from high computational complexity. Recently, Mamba has garnered widespread attention due to its superior long-range modeling capabilities with linear complexity. Nevertheless, Mamba demonstrates notable limitations when directly applied to MMRLC, including limited local contextual modeling capacity, suboptimal multi-modal feature fusion and lack of a task-specific spatial continuity scanning strategy. Hence, to fully explore the potential of Mamba in multi-modal land cover classification, we propose LSFMamba, which comprises multiple hierarchically connected local-enhanced fusion Mamba (LFM) modules. Within each LFM module, a local-enhanced visual state space (LVSS) block is designed to extract features from different modalities, while a cross-modal interaction state space (CISS) block is created to fuse these multi-modal features. In the LVSS block, we integrate a multi-kernel CNN block into the gating branch in Mamba to enhance its local modeling capabilities. In the CISS block, features from different modalities are interleaved, facilitating cross-modal feature interaction through the state space model. Furthermore, we introduce a novel spiral scanning strategy to reassess the significance of central pixels, a design driven by the unique characteristics of pixel-wise classification task. Extensive experimental results on three multi-modal remote sensing datasets demonstrate that the proposed LSFMamba achieves state-of-the-art performance with lower complexity. The code will be released at https://github.com/hhchhang78/LSFMamba.
- 6 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (5) , 6081-6094
Top Cited PapersLSFMamba: Local-Enhanced Spiral Fusion Mamba for Multi-Modal Land Cover Classification
Multi-modal learning, which fuses complementary information from different modalities, has significantly improved the accuracy of land cover classification, especially under adverse conditions like cloudy or rainy weather. Recent advancements in multi-modal remote sensing land cover classification (MMRLC) have witnessed the efficacy of approaches based on CNN and Transformer. However, CNN exhibits limitations in capturing long-range dependencies, whereas Transformer suffers from high computational complexity. Recently, Mamba has garnered widespread attention due to its superior long-range modeling capabilities with linear complexity. Nevertheless, Mamba demonstrates notable limitations when directly applied to MMRLC, including limited local contextual modeling capacity, suboptimal multi-modal feature fusion and lack of a task-specific spatial continuity scanning strategy. Hence, to fully explore the potential of Mamba in multi-modal land cover classification, we propose LSFMamba, which comprises multiple hierarchically connected local-enhanced fusion Mamba (LFM) modules. Within each LFM module, a local-enhanced visual state space (LVSS) block is designed to extract features from different modalities, while a cross-modal interaction state space (CISS) block is created to fuse these multi-modal features. In the LVSS block, we integrate a multi-kernel CNN block into the gating branch in Mamba to enhance its local modeling capabilities. In the CISS block, features from different modalities are interleaved, facilitating cross-modal feature interaction through the state space model. Furthermore, we introduce a novel spiral scanning strategy to reassess the significance of central pixels, a design driven by the unique characteristics of pixel-wise classification task. Extensive experimental results on three multi-modal remote sensing datasets demonstrate that the proposed LSFMamba achieves state-of-the-art performance with lower complexity. The code will be released at https://github.com/hhchhang78/LSFMamba.
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-15
Deep Symmetric Fusion Transformer for Multimodal Remote Sensing Data Classification
In recent years, multimodal remote sensing data classification (MMRSC) has evoked growing attention due to its more comprehensive and accurate delineation of Earth’s surface compared to its single-modal counterpart. However, it remains challenging to capture and integrate local and global features from single-modal data. Moreover, how to fully excavate and exploit the interactions between different modalities is still an intricate issue. To this end, we propose a novel dual-branch transformer-based framework named deep symmetric fusion transformer (DSymFuser). Within the framework, each branch contains a stack of local-global mixture (LGM) blocks, to extract hierarchical and discriminative single-modal features. In each LGM block, a local-global feature mixer with learnable weights is specifically devised to adaptively aggregate the local and global features extracted with a CNN-transformer network. Furthermore, we innovatively design a symmetric fusion transformer (SFT) which trails behind each LGM block. The elaborately-designed SFT facilitates cross-modal correlation excavation in a symmetric manner, comprehensively exploiting the complementary cues underlying heterogeneous modalities. The hierarchical construction of the LGM and SFT blocks enables feature extraction and fusion in a multilevel manner, further promoting the completeness and descriptiveness of the learnt features. We conducted extensive ablation studies and comparative experiments on three benchmark datasets, and the experimental results validated the effectiveness and superiority of the proposed method. The source code of the proposed method will be available publicly at https://github.com/HaixiaBi1982/DSymFuser.
- 14 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-15
Deep Symmetric Fusion Transformer for Multimodal Remote Sensing Data Classification
In recent years, multimodal remote sensing data classification (MMRSC) has evoked growing attention due to its more comprehensive and accurate delineation of Earth’s surface compared to its single-modal counterpart. However, it remains challenging to capture and integrate local and global features from single-modal data. Moreover, how to fully excavate and exploit the interactions between different modalities is still an intricate issue. To this end, we propose a novel dual-branch transformer-based framework named deep symmetric fusion transformer (DSymFuser). Within the framework, each branch contains a stack of local-global mixture (LGM) blocks, to extract hierarchical and discriminative single-modal features. In each LGM block, a local-global feature mixer with learnable weights is specifically devised to adaptively aggregate the local and global features extracted with a CNN-transformer network. Furthermore, we innovatively design a symmetric fusion transformer (SFT) which trails behind each LGM block. The elaborately-designed SFT facilitates cross-modal correlation excavation in a symmetric manner, comprehensively exploiting the complementary cues underlying heterogeneous modalities. The hierarchical construction of the LGM and SFT blocks enables feature extraction and fusion in a multilevel manner, further promoting the completeness and descriptiveness of the learnt features. We conducted extensive ablation studies and comparative experiments on three benchmark datasets, and the experimental results validated the effectiveness and superiority of the proposed method. The source code of the proposed method will be available publicly at https://github.com/HaixiaBi1982/DSymFuser.
- 8 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-14
Cross-Attention-Driven Adaptive Graph Relational Network for Multilabel Remote Sensing Scene Classification
Multi-label remote sensing scene classification (MLRSSC) has garnered growing attention in recent years, owing to its more comprehensive description of land covers compared to its single-label counterpart. However, challenges arise inevitably. First, the relations among multiple scene labels are sophisticated. How to excavate the inter-class dependencies is therefore a key challenge for the MLRSSC task. Second, extracting discriminative semantic features is essential yet challenging for scene prediction of remote sensing images. Another issue is that the multi-label dataset usually shows two-fold sample imbalances, i.e., class imbalance and positive-negative imbalance, which has not been explored in MLRSSC tasks so far. To overcome the above hurdles, we put forward a cross-attention-driven adaptive graph relational network for the MLRSSC task. Different from the chain-like long short-term memory (LSTM) or static label co-occurrence matrices, we propose to use image-specific relational graphs to dynamically model the inter-class dependencies. We innovatively devise a cross-attention-driven representation learning approach, which uses learnable label embeddings to query the class-wise semantic features, explicitly establishing the feature-label connections. Moreover, we design a balanced focal loss function, where the loss contributions of positive and negative samples are rebalanced based on the respective imbalance degrees of diverse classes. Extensive experiments were performed on UCM, AID, and DFC15 multi-label datasets. Experimental results demonstrated that our proposed method achieves state-of-the-art performance in the studied task.
- 8 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-14
Cross-Attention-Driven Adaptive Graph Relational Network for Multilabel Remote Sensing Scene Classification
Multi-label remote sensing scene classification (MLRSSC) has garnered growing attention in recent years, owing to its more comprehensive description of land covers compared to its single-label counterpart. However, challenges arise inevitably. First, the relations among multiple scene labels are sophisticated. How to excavate the inter-class dependencies is therefore a key challenge for the MLRSSC task. Second, extracting discriminative semantic features is essential yet challenging for scene prediction of remote sensing images. Another issue is that the multi-label dataset usually shows two-fold sample imbalances, i.e., class imbalance and positive-negative imbalance, which has not been explored in MLRSSC tasks so far. To overcome the above hurdles, we put forward a cross-attention-driven adaptive graph relational network for the MLRSSC task. Different from the chain-like long short-term memory (LSTM) or static label co-occurrence matrices, we propose to use image-specific relational graphs to dynamically model the inter-class dependencies. We innovatively devise a cross-attention-driven representation learning approach, which uses learnable label embeddings to query the class-wise semantic features, explicitly establishing the feature-label connections. Moreover, we design a balanced focal loss function, where the loss contributions of positive and negative samples are rebalanced based on the respective imbalance degrees of diverse classes. Extensive experiments were performed on UCM, AID, and DFC15 multi-label datasets. Experimental results demonstrated that our proposed method achieves state-of-the-art performance in the studied task.