Transfer learning RGB models to hyperspectral images with trainable tensor decompositions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917540382375936 |
|---|---|
| author | Schönfeld, Mariette Devos, Laurens Meert, Wannes Blockeel, Hendrik |
| author_facet | Schönfeld, Mariette Devos, Laurens Meert, Wannes Blockeel, Hendrik |
| contents | Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. However, these networks assume the input images to have 3 input channels, making them incompatible with multi- or hyperspectral images. Current approaches that mitigate this incompatibility sacrifice information in either the image, or the model. This work proposes a novel approach that preserves the image and spatial information present in the model by using partially trainable tensor decompositions. We create such decompositions of pretrained convolutional filters, separating the filters into spatial and spectral components. The spectral components are then replaced with trainable components of higher channel dimensionality. This creates hyperspectral filters that can specialize to new datasets, while retaining the spatial patterns of the original filter. Experiments on a variety of hyperspectral datasets show that our approach is more accurate and robust than other hyperspectral transfer learning methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28331 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Transfer learning RGB models to hyperspectral images with trainable tensor decompositions Schönfeld, Mariette Devos, Laurens Meert, Wannes Blockeel, Hendrik Computer Vision and Pattern Recognition Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. However, these networks assume the input images to have 3 input channels, making them incompatible with multi- or hyperspectral images. Current approaches that mitigate this incompatibility sacrifice information in either the image, or the model. This work proposes a novel approach that preserves the image and spatial information present in the model by using partially trainable tensor decompositions. We create such decompositions of pretrained convolutional filters, separating the filters into spatial and spectral components. The spectral components are then replaced with trainable components of higher channel dimensionality. This creates hyperspectral filters that can specialize to new datasets, while retaining the spatial patterns of the original filter. Experiments on a variety of hyperspectral datasets show that our approach is more accurate and robust than other hyperspectral transfer learning methods. |
| title | Transfer learning RGB models to hyperspectral images with trainable tensor decompositions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.28331 |