# Exploring the high dimensional geometry of HSI features

arXiv: https://arxiv.org/abs/2103.01303 · HTML: https://mlsanity.com/paper/2103.01303/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 9 references that are in the map.
- First posted on arXiv 1 Mar 2021.

## Builds on (most cited first, 2 of 2)

- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Neural collapse with unconstrained features](https://mlsanity.com/paper/2011.11619/) (2020)

## Abstract (arXiv)

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.