Exploring the high dimensional geometry of HSI features
This work provides insights into feature space geometries for hyperspectral imaging researchers, but it is incremental as it compares existing methods without introducing new techniques.
The study analyzed the geometric properties of hyperspectral image features from two methods, comparing them to raw features and linking them to neural collapse, but did not report specific numerical results.
We explore feature space geometries induced by the 3-D Fourier scattering transform and deep neural network with extended attribute profiles on four standard hyperspectral images. We examine the distances and angles of class means, the variability of classes, and their low-dimensional structures. These statistics are compared to that of raw features, and our results provide insight into the vastly different properties of these two methods. We also explore a connection with the newly observed deep learning phenomenon of neural collapse.