Source code for "MixerSENet: A Lightweight Framework for Efficient Hyperspectral Image Classification" Accepted for publication in IEEE Geoscience and Remote Sensing Letter (GRSL).
Paper Link: https://ieeexplore.ieee.org/document/11186508
Python 3.9.18, Tensorflow (and Keras) 2.10.0.
The evaluation is performed on two widely used hyperspectral datasets: Houston13 and QUH-Qingyun. link to the datasets along their class maps is available at: https://mega.nz/folder/zoJDhJKI#bNj3Xr0iLenBN12QdmGccw
To quantitatively measure the proposed MixerSENet model, three evaluation metrics are employed to verify the effectiveness of the algorithm, Overall Accuracy (OA), Average Accuracy (AA) and Cohen's Kappa (k). Also, Each class accuracy has been reported.
@ARTICLE{11186508, author={Alkhatib, Mohammed Q. and Kumar Roy, Swalpa and Jamali, Ali}, journal={IEEE Geoscience and Remote Sensing Letters}, title={MixerSENet: A Lightweight Framework for Efficient Hyperspectral Image Classification}, year={2025}, volume={22}, number={}, pages={1-5}, doi={10.1109/LGRS.2025.3616338}}