Regularized CNN Feature Hierarchy for Hyperspectral Image Classification

Convolutional Neural Networks (CNN) have been rigorously studied for Hyperspectral Image Classification (HSIC) and are known to be effective in exploiting joint spatial-spectral information with the expense of lower generalization performance learning speed due hard labels non-uniform distribution over labels. Therefore, this paper proposed an idea enhance CNN HSIC using soft that a weighted average uniform ground The method helps prevent from becoming over-confident. We empirically show that, improving performance, regularization also improves model calibration, which significantly beam-search. Several publicly available datasets used validate experimental evaluation, reveals improved as compared state-of-the-art models overall 99.29%, 99.97%, 100.0% accuracy Indiana Pines, Pavia University, Salinas dataset, respectively.