Article · International Journal of Remote Sensing · June 30, 2025

Self-supervised spatial-spectral transformer with Extreme Learning Machine for Hyperspectral Image Classification

Muhammad Imran Ahmad, Manuel Mazzara, Salvatore Distefano, Adil Khan, Xin Wu

Abstract

While deep learning has significantly advanced hyperspectral image (HSI) classification, capturing complex spatial-spectral features efficiently and achieving robust performance with limited dynamic masking within masked image sparse attention mechanism enhances computational efficiency by selectively attending to key spectral-spatial patches, effectively reducing complexity, without compromising classification performance. An Extreme Learning Machine (ELM) is integrated as the final classification layer, leveraging SST-extracted features for efficient and lightweight classification. The resulting hybrid SST-ELM model achieves 99.93% overall accuracy on the Salinas dataset, improving upon the baseline by 1.12% with a 5 reduction in training time. Similar improvements are observed on Pavia University (99.06%), Longkou (99.83%), Hanchuan (96.04%), and Honghu (97.10%) datasets.

Remote-Sensing Image ClassificationAdvanced Image Fusion TechniquesAdvanced Neural Network Applicationshyperspectral image classificationself-supervised learningextreme learning machine

Self-supervised spatial-spectral transformer with Extreme Learning Machine for Hyperspectral Image Classification

Abstract

More by Manuel Mazzara