轻量正则化可低成本实现扩散模型的稳定生成
An Analysis of Regularization and Fokker-Planck Residuals in Diffusion Models for Image Generation
- 用简单正则项替代复杂惩罚，降低计算开销
- 弱化FP残差能提升图像生成质量，强约束反而无效
- 适合关注效率与稳定性平衡的研究者
近期研究表明，采用去噪得分匹配（DSM）目标训练的扩散模型常违背真实数据密度演化的福克-普朗克（FP）方程。直接在目标函数中惩罚这些偏差虽能减小残差，但带来显著计算开销。同时发现，严格遵守FP方程并不必然提升生成样本质量，最佳结果往往出现在较弱的FP正则化下。本文通过实证分析多种轻量级正则化方法，研究其对FP残差和生成质量的影响，结果表明：在大幅降低计算成本的前提下，仍可获得与强正则化相当的收益。代码已开源。
原文摘要 · Abstract (English)
Recent work has shown that diffusion models trained with the denoising score matching (DSM) objective often violate the Fokker--Planck (FP) equation that governs the evolution of the true data density. Directly penalizing these deviations in the objective function reduces their magnitude but introduces a significant computational overhead. It is also observed that enforcing strict adherence to the FP equation does not necessarily lead to improvements in the quality of the generated samples, as often the best results are obtained with weaker FP regularization. In this paper, we investigate whether simpler penalty terms can provide similar benefits. We empirically analyze several lightweight regularizers, study their effect on FP residuals and generation quality, and show that the benefits of FP regularization are available at substantially lower computational cost. Our code is available at https://github.com/OnnoNiemann/fp_diffusion_analysis.
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。