Hyperspectral Benchmark: Bridging the Gap between HSI Applications through Comprehensive Dataset and Pretraining

TL;DR

This paper introduces a comprehensive hyperspectral imaging benchmark dataset across diverse applications, enabling better evaluation of models and proposing a pretraining pipeline to improve training stability for large models in data-scarce scenarios.

Contribution

It provides a new diverse benchmark dataset for hyperspectral imaging applications and develops a pretraining pipeline to enhance model training stability.

Findings

Benchmark dataset covers food inspection, remote sensing, recycling

Pretraining improves training stability for large models

Facilitates better evaluation and development of hyperspectral models

Abstract

Hyperspectral Imaging (HSI) serves as a non-destructive spatial spectroscopy technique with a multitude of potential applications. However, a recurring challenge lies in the limited size of the target datasets, impeding exhaustive architecture search. Consequently, when venturing into novel applications, reliance on established methodologies becomes commonplace, in the hope that they exhibit favorable generalization characteristics. Regrettably, this optimism is often unfounded due to the fine-tuned nature of models tailored to specific HSI contexts. To address this predicament, this study introduces an innovative benchmark dataset encompassing three markedly distinct HSI applications: food inspection, remote sensing, and recycling. This comprehensive dataset affords a finer assessment of hyperspectral model capabilities. Moreover, this benchmark facilitates an incisive examination of prevailing state-of-the-art techniques, consequently fostering the evolution of superior methodologies. Furthermore, the enhanced diversity inherent in the benchmark dataset underpins the establishment of a pretraining pipeline for HSI. This pretraining regimen serves to enhance the stability of training processes for larger models. Additionally, a procedural framework is delineated, offering insights into the handling of applications afflicted by limited target dataset sizes.