从分类器中心视角探究（无）分类器引导机制

Studying Classifier(-Free) Guidance From a Classifier-Centric Perspective

March 13, 2025

作者: Xiaoming Zhao, Alexander G. Schwing

cs.AI

摘要

无分类器引导已成为条件生成任务中降噪扩散模型的标准配置。然而，对于无分类器引导的全面理解仍显不足。本研究通过实证分析，为无分类器引导提供了新的视角。具体而言，我们不仅关注无分类器引导，更追溯其根源——分类器引导，明确推导过程中的关键假设，并系统性地探讨了分类器的作用。研究发现，无论是分类器引导还是无分类器引导，都是通过将降噪扩散轨迹推离决策边界来实现条件生成的，这些边界区域通常是条件信息相互交织且难以学习的区域。基于这一以分类器为核心的理解，我们提出了一种基于流匹配的通用后处理步骤，旨在缩小预训练降噪扩散模型所学分布与真实数据分布之间的差距，特别是在决策边界附近。多项数据集上的实验验证了所提方法的有效性。

English

Classifier-free guidance has become a staple for conditional generation with denoising diffusion models. However, a comprehensive understanding of classifier-free guidance is still missing. In this work, we carry out an empirical study to provide a fresh perspective on classifier-free guidance. Concretely, instead of solely focusing on classifier-free guidance, we trace back to the root, i.e., classifier guidance, pinpoint the key assumption for the derivation, and conduct a systematic study to understand the role of the classifier. We find that both classifier guidance and classifier-free guidance achieve conditional generation by pushing the denoising diffusion trajectories away from decision boundaries, i.e., areas where conditional information is usually entangled and is hard to learn. Based on this classifier-centric understanding, we propose a generic postprocessing step built upon flow-matching to shrink the gap between the learned distribution for a pre-trained denoising diffusion model and the real data distribution, majorly around the decision boundaries. Experiments on various datasets verify the effectiveness of the proposed approach.