2026/01/01 by Thibault de Surrel, Charlotte Boucherie, Florian Yger · 1 voice
Computer Science · #Generative Adversarial Networks and Image Synthesis #Face recognition and analysis #Domain Adaptation and Few-Shot Learning
paper · pdf · doi:10.14428/esann/2026.es2026-158
openalex publication_date 2026/01/01 · openalex created_date 2026/04/17 · openalex updated_date 2026/07/29
When building dimension reduction methods tailored for Symmetric Positive Definite (SPD) matrices, it is crucial to account for their Riemannian geometry.In this work, we propose an SPDNet-based autoencoder, that we call SPDNet-AE, that learns low-dimensional SPD representations of high-dimensional SPD matrices while preserving the geometry throughout the network.The SPDNet-AE is built using the BiMap layer of the SPDNet, but we allow it to have multiple channels.We show that our SPDNet-AE is able to learn a useful low-dimensional representation of the data for classification (without any class information).Moreover, we show that with a comparable number of parameters, a classical Euclidean autoencoder is not able to learn and maintain the SPD constraint on the input matrices.