SpectralTrain: A Universal Framework for Hyperspectral Image Classification

TL;DR

SpectralTrain is a versatile training framework for hyperspectral image classification that combines curriculum learning and PCA-based spectral downsampling to improve efficiency and generalization across models and datasets.

Contribution

It introduces a universal, architecture-agnostic training method that reduces training time significantly while maintaining accuracy, applicable to classical and state-of-the-art models.

Findings

Achieves 2-7x training speedup with minimal accuracy loss.

Demonstrates strong generalization across diverse datasets and spectral characteristics.

Effective in climate-related remote sensing tasks like cloud classification.

Abstract

Hyperspectral image (HSI) classification typically involves large-scale data and computationally intensive training, which limits the practical deployment of deep learning models in real-world remote sensing tasks. This study introduces SpectralTrain, a universal, architecture-agnostic training framework that enhances learning efficiency by integrating curriculum learning (CL) with principal component analysis (PCA)-based spectral downsampling. By gradually introducing spectral complexity while preserving essential information, SpectralTrain enables efficient learning of spectral -- spatial patterns at significantly reduced computational costs. The framework is independent of specific architectures, optimizers, or loss functions and is compatible with both classical and state-of-the-art (SOTA) models. Extensive experiments on three benchmark datasets -- Indian Pines, Salinas-A, and the newly introduced CloudPatch-7 -- demonstrate strong generalization across spatial scales, spectral characteristics, and application domains. The results indicate consistent reductions in training time by 2-7x speedups with small-to-moderate accuracy deltas depending on backbone. Its application to cloud classification further reveals potential in climate-related remote sensing, emphasizing training strategy optimization as an effective complement to architectural design in HSI models. Code is available at https://github.com/mh-zhou/SpectralTrain.