3D/2D regularized CNN feature hierarchy for Hyperspectral image classification

TL;DR

This paper introduces a regularized CNN approach for hyperspectral image classification that uses soft labels to improve generalization, calibration, and performance over state-of-the-art models across multiple datasets.

Contribution

It proposes a novel soft label regularization technique for CNNs in hyperspectral image classification to enhance generalization and calibration.

Findings

Improved generalization performance on multiple datasets

Enhanced model calibration through label smoothing

Reduced computational complexity compared to existing models

Abstract

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 and learning speed due to the hard labels and non-uniform distribution over labels. Several regularization techniques have been used to overcome the aforesaid issues. However, sometimes models learn to predict the samples extremely confidently which is not good from a generalization point of view. Therefore, this paper proposed an idea to enhance the generalization performance of a hybrid CNN for HSIC using soft labels that are a weighted average of the hard labels and uniform distribution over ground labels. The proposed method helps to prevent CNN from becoming over-confident. We empirically show that in improving generalization performance, label smoothing also improves model calibration which significantly improves beam-search. Several publicly available Hyperspectral datasets are used to validate the experimental evaluation which reveals improved generalization performance, statistical significance, and computational complexity as compared to the state-of-the-art models. The code will be made available at https://github.com/mahmad00.