Structured Generations: Using Hierarchical Clusters to guide Diffusion Models
This work addresses limitations in VAE-based generative modeling for image generation, offering an incremental improvement in clustering-based approaches.
The paper tackled the problem of generating high-quality and cluster-representative images by integrating hierarchical clustering into diffusion models, resulting in improved image clarity and distinct samples for each data cluster.
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.