Wavelength-aware 2D Convolutions for Hyperspectral Imaging
This work solves data efficiency and interoperability problems for hyperspectral imaging researchers and practitioners, though it appears incremental as it builds on existing 2D convolution methods.
The paper tackles the challenges of training deep learning models on small hyperspectral imaging datasets by proposing a wavelength-aware 2D convolution that addresses large channel dimensions and camera incompatibility, achieving superior performance in applications like inline inspection and remote sensing.
Deep Learning could drastically boost the classification accuracy for Hyperspectral Imaging (HSI). Still, the training on the mostly small hyperspectral data sets is not trivial. Two key challenges are the large channel dimension of the recordings and the incompatibility between cameras of different manufacturers. By introducing a suitable model bias and continuously defining the channel dimension, we propose a 2D convolution optimized for these challenges of Hyperspectral Imaging. We evaluate the method based on two different hyperspectral applications (inline inspection and remote sensing). Besides the shown superiority of the model, the modification adds additional explanatory power. In addition, the model learns the necessary camera filters in a data-driven manner. Based on these camera filters, an optimal camera can be designed.