Prospects for Mitigating Spectral Variability in Tropical Species Classification Using Self-Supervised Learning
This work addresses the challenge of spectral variability for researchers and practitioners in remote sensing and ecology, but it is incremental as it applies an existing SSL method to a specific domain problem.
The paper tackled the problem of spectral variability hindering consistent tropical species classification from airborne hyperspectral imaging by using Self-Supervised Learning (SSL) to develop robust features, resulting in a 10-point accuracy improvement in robustness across dates for classifying 40 species.
Airborne hyperspectral imaging is a promising method for identifying tropical species, but spectral variability between acquisitions hinders consistent results. This paper proposes using Self-Supervised Learning (SSL) to encode spectral features that are robust to abiotic variability and relevant for species identification. By employing the state-of-the-art Barlow-Twins approach on repeated spectral acquisitions, we demonstrate the ability to develop stable features. For the classification of 40 tropical species, experiments show that these features can outperform typical reflectance products in terms of robustness to spectral variability by 10 points of accuracy across dates.