You can also find my articles on my Google Scholar profile.
Published in AAAI, 2025
MTL-LoRA enhances LoRA by improving the adaptation of large language models to multiple tasks simultaneously. It leverages task-specific transformation matrices and multiple up-projection matrices to effectively extract both task-specific and task-agnostic information
Download here
Under Review
StreamAdapter directly maps context into model parameter updates at test time without backpropagation, achieving in-context learning like test time adaptation capabilities without requiring explicit documentation or demonstrations in the context.
Download here
Published in ECCV, 2024
Develop a large-scale pre-training and instruction dataset, and construct a multimodal large language model, LHRS-Bot, with an innovative alignment strategy. LHRS-Bot showcases superior performance on holistic understanding of remote sensing images and complex visual reasoning.
Recommended citation: Muhtar, D., Li, Z., Gu, F., Zhang, X., & Xiao, P. (2024). LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model. arXiv preprint arXiv:2402.02544. https://arxiv.org/abs/2402.02544
Published in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023
A full-scale difference feature fusion network (FDFF-Net) for change detection, which can alleviate pseudochanges and reduce the loss of change details during detection
Recommended citation: Gu, F., Xiao, P., Zhang, X., Li, Z., & Muhtar, D.. (2023). FDFF-Net: A Full-Scale Difference Feature Fusion Network for Change Detection in High-Resolution Remote Sensing Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. https://ieeexplore.ieee.org/abstract/document/10324305
Published in IEEE Transactions on Geoscience and Remote Sensing, 2023
Integrating contrast learning and masked image modeling to enhance self-supervised pre-trained representation learning. Pre-training on the large scale MillionAID dataset, showing SOTA performance across different remote sensing downstream tasks. (Outperform MAE, MoCo, SwAV, and SimMIM, etc.).
Recommended citation: Muhtar, D., Zhang, X., Xiao, P., Li, Z., & Gu, F. (2023). CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding. IEEE Transactions on Geoscience and Remote Sensing. https://arxiv.org/abs/2304.09670
Published in IEEE Geoscience and Remote Sensing Letters, 2023
A lightweight dual-range context aggregation network (LDCANet) for efficient remote sensing image semantic segmentation.
Recommended citation: He, G., Dong, Z., Feng, P., Muhtar, D., & Zhang, X. (2023). Dual-Range Context Aggregation for Efficient Semantic Segmentation in Remote Sensing Images. IEEE Geoscience and Remote Sensing Letters, 20, 1-5. https://ieeexplore.ieee.org/abstract/document/10005205
Published in IEEE Transactions on Geoscience and Remote Sensing, 2022
Employing position index to model intricate spatial relationships among various objects in remote sensing images, facilitating fine-grained representation learning.
Recommended citation: Muhtar, D., Zhang, X., Xiao, P., Li, Z., & Gu, F. (2023). CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding. IEEE Transactions on Geoscience and Remote Sensing. https://ieeexplore.ieee.org/abstract/document/9781429