Structure-Preserving Transformers for Sequences of SPD Matrices

Code

• github.com/mathieuseraphim/spdtransnet
  OfficialIn paperpytorch★ 36
• github.com/MathieuSeraphim/SPDTransNet_plus
  pytorch★ 7

Abstract

In recent years, Transformer-based auto-attention mechanisms have been successfully applied to the analysis of a variety of context-reliant data types, from texts to images and beyond, including data from non-Euclidean geometries. In this paper, we present such a mechanism, designed to classify sequences of Symmetric Positive Definite matrices while preserving their Riemannian geometry throughout the analysis. We apply our method to automatic sleep staging on timeseries of EEG-derived covariance matrices from a standard dataset, obtaining high levels of stage-wise performance.

Tasks

Benchmark Results

Reproductions