Hierarchical VAE with a Diffusion-based VampPrior

2024-12-02 · Anna Kuzina, Jakub M. Tomczak

Deep hierarchical variational autoencoders (VAEs) are powerful latent variable generative models. In this paper, we introduce Hierarchical VAE with Diffusion-based Variational Mixture of the Posterior Prior (VampPrior). We apply amortization to scale the VampPrior to models with many stochastic layers. The proposed approach allows us to achieve better performance compared to the original VampPrior work and other deep hierarchical VAEs, while using fewer parameters. We empirically validate our method on standard benchmark datasets (MNIST, OMNIGLOT, CIFAR10) and demonstrate improved training stability and latent space utilization.

📄 PDF Abstract BibTeX arXiv:2412.01373

Code (1)

akuzina/dvp_vae 공식 구현 pytorch

Tasks

Density Estimation Image Generation

Methods 이 논문이 사용한 방법론

Hierarchical VAE 설명 없음

VAE with a VampPrior

2017-05-19 · Jakub M. Tomczak, Max Welling

Many different methods to train deep generative models have been introduced in the past. In this paper, we propose to extend the variational auto-encoder (VAE) framework with a new type of prior which we call "Variationa…

VAMP-Diff: VampPrior Latent Diffusion for Photoplethysmography Modeling

2026-05-17 · Fatemeh Ghasemi Balouei, Nathan Willemsen, Mahesh Banavar, Bahman Moraffah arxiv

Photoplethysmography (PPG) has become a ubiquitous physiological signal; however, current generative models still struggle to preserve realistic waveform morphology and learn a latent structure that captures cardiac and …

Hierarchical VampPrior Variational Fair Auto-Encoder

2018-06-26 · Philip Botros, Jakub M. Tomczak

Decision making is a process that is extremely prone to different biases. In this paper we consider learning fair representations that aim at removing nuisance (sensitive) information from the decision process. For this …

Decision Making Fairness

The VampPrior Mixture Model

2024-02-06 · Andrew Stirn, David A. Knowles

Current clustering priors for deep latent variable models (DLVMs) require defining the number of clusters a-priori and are susceptible to poor initializations. Addressing these deficiencies could greatly benefit deep lea…

Clustering Image Clustering model Unsupervised Image Classification+1

Enhancing VAEs for Collaborative Filtering: Flexible Priors & Gating Mechanisms

2019-11-03 · Daeryong Kim, Bongwon Suh

Neural network based models for collaborative filtering have started to gain attention recently. One branch of research is based on using deep generative models to model user preferences where variational autoencoders we…

Collaborative Filtering Recommendation Systems