.png){kind=icon}
Return
HVQ-VAE: Variational auto-encoder with hyperbolic vector quantization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.cviu.2025.104392.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
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.
Journal
IF:
3.5
Papers:
555
Citations:
7.3K
Organization
No organization information available
Cited Papers
ShareSaveShareSaveShareSaveShareSaveGradient-based Hierarchical Clustering using Continuous Representations of Trees in Hyperbolic Space.png)
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
OAAI
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningIF0
OAAIShareSave
View more