Prospects for Mitigating Spectral Variability in Tropical Species Classification Using Self-Supervised Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910878644830208 |
|---|---|
| author | Prieur, Colin Braham, Nassim Ait Ali Tresson, Paul Vincent, Grégoire Chanussot, Jocelyn |
| author_facet | Prieur, Colin Braham, Nassim Ait Ali Tresson, Paul Vincent, Grégoire Chanussot, Jocelyn |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12973 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prospects for Mitigating Spectral Variability in Tropical Species Classification Using Self-Supervised Learning Prieur, Colin Braham, Nassim Ait Ali Tresson, Paul Vincent, Grégoire Chanussot, Jocelyn Computer Vision and Pattern Recognition 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. |
| title | Prospects for Mitigating Spectral Variability in Tropical Species Classification Using Self-Supervised Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12973 |