Ali Jamali's Projects
Here is the code developed for the paper "A deep learning framework based on generative adversarial networks and vision transformer for complex wetland classification using limited training samples" puplished in International Journal of Applied Earth Observation and Geoinformation.
Here are the codes for the "3DUNetGSFormer: A deep learning pipeline for complex wetland mapping using generative adversarial networks and Swin transformer" paper.
This Keras code is for the paper A. Jamali, Ali and Roy, Swalpa Kumar and Hong, Danfeng and Atkinson, Peter M and Ghamisi, Pedram, "[Attention Graph Convolutional Network for Disjoint Hyperspectral Image Classification]," in IEEE Geoscience and Remote Sensing Letters, doi: 10.1109/LGRS.2024.335642 [https://ieeexplore.ieee.org/document/10409250].
This code is for the paper "PolSAR Image Classification based on Deep Convolutional Neural Networks and Wavelet Transformation" that is published in the IEEE Geoscience and Remote Sensing Letters journal.
Here are the codes for the "Deep Forest classifier for wetland mapping using the combination of Sentinel-1 and Sentinel-2 data" paper.
This code is for the paper "e-TransUNet: TransUNet provides a strong spatial transformation for precise deforestation mapping" that is published in the Remote Sensing Applications: Society and Environment. journal.
How to Learn More? Exploring the Possibility of Kolmogorov-Arnold Networks for Hyperspectral Image Classification
Here are the codes for the "Swin Transformer and Deep Convolutional Neural Networks for Coastal Wetland Classification using Sentinel-1, Sentinel-2, and LiDAR Data" paper.
This code is for the paper "Local Window Attention Transformer for Polarimetric SAR Image Classification" that is published in the IEEE Geoscience and Remote Sensing Letters journal.
This Keras code is for the paper A. Jamali, S. K. Roy, J. Li and P. Ghamisi, "[Neighborhood Attention Makes the Encoder of ResUNet Stronger for Accurate Road Extraction]," in IEEE Geoscience and Remote Sensing Letters, doi: 10.1109/LGRS.2024.3354560 [https://ieeexplore.ieee.org/document/10400502].
This Keras code is for the paper Residual wave vision U-Net for flood mapping using dual polarization Sentinel-1 SAR imageryโ
This Keras code is for the paper A. Jamali, Ali and Roy, Swalpa Kumar and Hong, Danfeng and Atkinson, Peter M and Ghamisi, Pedram, "[Spatial Gated Multi-Layer Perceptron for Land Use and Land Cover Mapping]," in IEEE Geoscience and Remote Sensing Letters, doi: 10.1109/LGRS.2024.3354175 [https://ieeexplore.ieee.org/document/10399888/]
SimPoolFormer: A Two-Stream Vision Transformer for Hyperspectral Image Classification
Here are the codes for the "TransU-Net++: Rethinking attention gated TransU-Net for deforestation mapping" paper.
This project fine-tune a pretrained Google Vision Transformer (ViT) model on the NWPU-RESISC45 dataset using the Hugging Face Transformers library.
Here are the codes for the "WetMapFormer: A unified deep CNN and vision transformer for complex wetland mapping" paper.