Supervised Embedded Methods for Hyperspectral Band Selection

TL;DR

This paper introduces two supervised embedded methods for hyperspectral band selection that integrate directly into deep learning models, achieving state-of-the-art results with minimal bands for remote sensing and autonomous driving applications.

Contribution

The paper presents novel task-specific embedded band selection methods that unify feature selection with model training, improving efficiency and performance over prior approaches.

Findings

Achieved state-of-the-art accuracy on three remote sensing benchmarks.

Selected minimal number of bands while maintaining high performance.

Demonstrated effectiveness on autonomous driving dataset.

Abstract

Hyperspectral Imaging (HSI) captures rich spectral information across contiguous wavelength bands, supporting applications in precision agriculture, environmental monitoring, and autonomous driving. However, its high dimensionality poses computational challenges, particularly in real-time or resource-constrained settings. While prior band selection methods attempt to reduce complexity, they often rely on separate preprocessing steps and lack alignment with downstream tasks. We propose two novel supervised, embedded methods for task-specific HSI band selection that integrate directly into deep learning models. By embedding band selection within the training pipeline, our methods eliminate the need for separate preprocessing and ensure alignment with the target task. Extensive experiments on three remote sensing benchmarks and an autonomous driving dataset show that our methods achieve state-of-the-art performance while selecting only a minimal number of bands. These results highlight the potential of efficient, task-specific HSI pipelines for practical deployment.