通过调整得分函数的尖锐度，有效减少扩散模型生成幻觉样本。
Laplacian Score Sharpening for Mitigating Hallucination in Diffusion Models
- 引入拉普拉斯值修正推理时的得分函数，抑制模式插值现象。
- 在1D/2D与高维图像数据上，幻觉样本率显著下降。
- 方法适用于无条件扩散模型，尤其适合追求生成真实性的场景。
扩散模型虽表现优异，但常产生不连贯或不真实的样本（即幻觉）。现有研究指出这源于模式插值与得分平滑，但缺乏采样过程中的抑制方法。本文提出一种推理阶段的后处理得分函数修正策略，利用得分的拉普拉斯值（或称尖锐度）来缓解无条件扩散模型在1维、2维及高维图像数据中的模式插值幻觉。我们基于有限差分版的Hutchinson迹估计器，实现了高维情形下的高效拉普拉斯近似。实验表明，该修正能显著降低玩具型1D/2D分布及高维图像数据集上的幻觉样本率。此外，分析揭示了拉普拉斯值与得分不确定性之间的关联。
原文摘要 · Abstract (English)
Diffusion models, though successful, are known to suffer from hallucinations that create incoherent or unrealistic samples. Recent works have attributed this to the phenomenon of mode interpolation and score smoothening, but they lack a method to prevent their generation during sampling. In this paper, we propose a post-hoc adjustment to the score function during inference that leverages the Laplacian (or sharpness) of the score to reduce mode interpolation hallucination in unconditional diffusion models across 1D, 2D, and high-dimensional image data. We derive an efficient Laplacian approximation for higher dimensions using a finite-difference variant of the Hutchinson trace estimator. We show that this correction significantly reduces the rate of hallucinated samples across toy 1D/2D distributions and a high-dimensional image dataset. Furthermore, our analysis explores the relationship between the Laplacian and uncertainty in the score.
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。