HVQ-VAE: Variational auto-encoder with hyperbolic vector quantization

Shangyu Chen

doi:10.1016/j.cviu.2025.104392

HVQ-VAE: Variational auto-encoder with hyperbolic vector quantization

2025-05-21

0

PRE

AI

DOI：10.1016/j.cviu.2025.104392

Original

Original request for help

Save

Abstract

En 中文

• This paper introduces HVQ-VAE enhancing traditional VQ-VAE with geometric priors. • The encoder of HVQ-VAE can learn the inherent hierarchical structures from the data. • Demonstrates superior image reconstruction and learning efficiency. • HVQ-VAE’s geometric prior leads to higher codebook usage, faster convergence, and improved performance. • HVQ-VAE employs Riemannian optimization to update the codebook within hyperbolic space.

HVQ-VAE: Variational auto-encoder with hyperbolic vector quantization

Abstract

Journal

Organization