统一扩散模型泛化行为的分析框架，提升生成质量
Filtered Posterior Mean Collections: A Unified Framework for Analytical Models of Diffusion Generalization
- 用查询精度向量与响应权重构建统一模型类
- 在三张自然图像数据集上实现一致的采样质量提升
- 适合研究扩散模型泛化机制与生成优化的学者
图像扩散模型的核心神经网络去噪函数在多种网络结构和训练超参数下表现出高度一致的泛化行为。近期研究尝试通过聚合训练数据块的后验加权平均来建模这些网络的输出。本文将此类方法整合为统一的模型类别，称为过滤后验均值集合（FPMC），通过查询精度向量、响应权重和源分布进行定义，并证明现有方法可通过特定设计选择还原。逐项分析各设计轴发现，对先验块方法进行软松弛以及扩展源分布可提升性能。将该改进应用于已有FPMC，在三个自然图像数据集上均实现一致的样本质量提升。
原文摘要 · Abstract (English)
The neural-network denoising functions which form the backbone of image diffusion models are remarkably consistent in their generalization behaviour across a wide variety of network architectures and training procedure hyperparameters. A recent line of research has sought to model the outputs of these networks by aggregating posterior weighted averages of training dataset patches. In this work, we consolidate these approaches into a unified model class which we call Filtered Posterior Mean Collections (FPMCs). We define this model class using query precision vectors, response weights, and source distributions, and illustrate that existing methods are recoverable with specific choices of these design axes. Investigating each axis in turn, we find that FPMC performance can be improved with soft relaxations of prior patch-based methods, and through augmentations of source distributions. Applying these findings to an existing FPMC, we demonstrate consistent sample improvement across three natural image datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。