Summary of Structured Generations: Using Hierarchical Clusters to Guide Diffusion Models, by Jorge Da Silva Goncalves et al.
Structured Generations: Using Hierarchical Clusters to guide Diffusion Models
by Jorge da Silva Goncalves, Laura Manduchi, Moritz Vandenhirtz, Julia E. Vogt
First submitted to arxiv on: 8 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Diffuse-TreeVAE model combines hierarchical clustering with Denoising Diffusion Probabilistic Models (DDPMs) to generate high-quality images representative of their respective clusters. This approach integrates a learned latent tree VAE-based structure, propagating through hierarchical paths and utilizing a second-stage DDPM to refine and generate distinct images for each data cluster. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new model that generates images by sampling from a root embedding and then refining them with a Denoising Diffusion Probabilistic Model (DDPM) is introduced. This approach ensures the generated images are representative of their respective clusters, addressing limitations in previous VAE-based methods. |
Keywords
» Artificial intelligence » Diffusion » Embedding » Hierarchical clustering » Probabilistic model
