Transfer learning RGB models to hyperspectral images with trainable tensor decompositions
This work enables transfer learning from RGB models to hyperspectral images without sacrificing spatial or spectral information, benefiting remote sensing and other hyperspectral imaging domains.
The paper proposes a method to adapt RGB-pretrained convolutional neural networks to hyperspectral images using partially trainable tensor decompositions, achieving higher accuracy and robustness compared to existing hyperspectral transfer learning approaches.
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.