paper-with-me

홈 › Papers

Structured Generations: Using Hierarchical Clusters to guide Diffusion Models

2024-07-08 · Jorge da Silva Goncalves, Laura Manduchi, Moritz Vandenhirtz, Julia E. Vogt

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.

📄 PDF Abstract BibTeX arXiv:2407.06124

Code (1)

JoGo175/diffuse-treevae 공식 구현 pytorch

Tasks

ClusteringDenoising

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Hierarchical Clustering for Conditional Diffusion in Image Generation

2024-10-22 · Jorge da Silva Goncalves, Laura Manduchi, Moritz Vandenhirtz, Julia E. Vogt

Finding clusters of data points with similar characteristics and generating new cluster-specific samples can significantly enhance our understanding of complex data distributions. While clustering has been widely explore…

ClusteringImage Generation

Demystify Protein Generation with Hierarchical Conditional Diffusion Models

2025-07-24 · Zinan Ling, Yi Shi, Brett McKinney, Da Yan 외 arxiv

Generating novel and functional protein sequences is critical to a wide range of applications in biology. Recent advancements in conditional diffusion models have shown impressive empirical performance in protein generat…

Protein Design

Hierarchically Structured Meta-learning

2019-05-13 · Huaxiu Yao, Ying WEI, Junzhou Huang, Zhenhui Li

In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handl…

ClusteringContinual LearningFew-Shot Image Classificationimage-classification+2

Diffusion Cocktail: Mixing Domain-Specific Diffusion Models for Diversified Image Generations

2023-12-12 · Haoming Liu, Yuanhe Guo, Shengjie Wang, Hongyi Wen

Diffusion models, capable of high-quality image generation, receive unparalleled popularity for their ease of extension. Active users have created a massive collection of domain-specific diffusion models by fine-tuning b…

Image GenerationImage ManipulationStyle Transfer

CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation

2026-01-09 · Yutong Song, Jiang Wu, Weijia Zhang, Chengze Shen 외 arxiv

Adapting large language models to individual users remains challenging due to the tension between fine-grained personalization and scalable deployment. We present CARD, a hierarchical framework that achieves effective pe…

Text Generation