Structured Generations: Using Hierarchical Clusters to Guide Diffusion Models
Abstract
This paper introduces Diffuse-TreeVAE, a deep generative model that integrates hierarchical clustering into the framework of Denoising Diffusion Probabilistic Models (DDPMs). The proposed approach generates new images by sampling from a root embedding of a learned latent tree VAE-based structure, it then propagates through hierarchical paths, and utilizes a second-stage DDPM to refine and generate distinct, high-quality images for each data cluster. The result is a model that not only improves image clarity but also ensures that the generated samples are representative of their respective clusters, addressing the limitations of previous VAE-based methods and advancing the state of clustering-based generative modeling.
Cite
Text
da Silva Gonçalves et al. "Structured Generations: Using Hierarchical Clusters to Guide Diffusion Models." ICML 2024 Workshops: SPIGM, 2024.Markdown
[da Silva Gonçalves et al. "Structured Generations: Using Hierarchical Clusters to Guide Diffusion Models." ICML 2024 Workshops: SPIGM, 2024.](https://mlanthology.org/icmlw/2024/dasilvagoncalves2024icmlw-structured/)BibTeX
@inproceedings{dasilvagoncalves2024icmlw-structured,
title = {{Structured Generations: Using Hierarchical Clusters to Guide Diffusion Models}},
author = {da Silva Gonçalves, Jorge and Manduchi, Laura and Vandenhirtz, Moritz and Vogt, Julia E},
booktitle = {ICML 2024 Workshops: SPIGM},
year = {2024},
url = {https://mlanthology.org/icmlw/2024/dasilvagoncalves2024icmlw-structured/}
}