Structured Generations: Using Hierarchical Clusters to guide Diffusion Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916320619003904 |
|---|---|
| author | Goncalves, Jorge da Silva Manduchi, Laura Vandenhirtz, Moritz Vogt, Julia E. |
| author_facet | Goncalves, Jorge da Silva Manduchi, Laura Vandenhirtz, Moritz Vogt, Julia E. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06124 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Structured Generations: Using Hierarchical Clusters to guide Diffusion Models Goncalves, Jorge da Silva Manduchi, Laura Vandenhirtz, Moritz Vogt, Julia E. Machine Learning Computer Vision and Pattern Recognition 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. |
| title | Structured Generations: Using Hierarchical Clusters to guide Diffusion Models |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.06124 |