Contrastive learning has demonstrated great success in representation learning, especially for image classification tasks. However, there is still a shortage in studies targeting regression tasks, and more specifically applications on hyperspectral data. In this paper, we propose a spectral-spatial contrastive learning framework for regression tasks for hyperspectral data, in a model-agnostic design allowing to enhance backbones such as 3D convolutional and transformer-based networks. Moreover, we provide a collection of transformations relevant for augmenting hyperspectral data. Experiments on synthetic and real datasets show that the proposed framework and transformations significantly improve the performance of all studied backbone models.
@article{arxiv.2602.10745,
title = {Spectral-Spatial Contrastive Learning Framework for Regression on Hyperspectral Data},
author = {Mohamad Dhaini and Paul Honeine and Maxime Berar and Antonin Van Exem},
journal= {arXiv preprint arXiv:2602.10745},
year = {2026}
}