arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.10326cs.CVcs.LG
收藏

带有不确定性量化和指导的流匹配

Flow Matching with Uncertainty Quantification and Guidance

MIT(麻省理工学院)

Juyeop Han, Lukas Lao Beyer, Sertac Karaman

AI总结:

本文提出UA-Flow,通过预测速度场和异方差不确定性提升流匹配生成质量,实验表明其不确定性信号更符合样本保真度,且不确定性指导进一步提升生成质量。

摘要:

尽管基于采样的生成模型如流匹配在样本生成上取得了显著成功,但它们仍可能生成不一致或质量下降的样本。为了评估样本可靠性并生成更高质量的输出,我们提出了不确定性感知的流匹配(UA-Flow),这是一种轻量级的流匹配扩展,能够同时预测速度场和异方差不确定性。UA-Flow通过将速度不确定性传播到流动力学中来估计每个样本的不确定性。这些不确定性估计作为样本可靠性的信号,我们进一步利用它们通过不确定性感知分类器指导和无分类器指导来引导生成。在图像生成实验中,UA-Flow产生的不确定性信号比基线方法更高度相关于样本保真度,且不确定性引导的采样进一步提高了生成质量。

英文摘要:

Despite the remarkable success of sampling-based generative models such as flow matching, they can still produce samples of inconsistent or degraded quality. To assess sample reliability and improve sample fidelity, we propose uncertainty-aware flow matching (UA-Flow), a lightweight extension of flow matching that predicts the velocity field together with heteroscedastic uncertainty. UA-Flow estimates spatially localized sample uncertainty by propagating velocity uncertainty through the flow dynamics. The resulting estimates serve as reliability signals that reflect data-manifold support for each generated sample or region. We further use them to steer generation via uncertainty-aware guidance (UG) and uncertainty-aware classifier-free guidance (UCFG). Experiments on ImageNet and CIFAR-10 show that UA-Flow's uncertainty tracks sample fidelity more consistently than element-wise baselines and that these signals also carry information about data-manifold support. On ImageNet, UG increases precision at the cost of recall and improves FID, while UCFG maintains lower FID than CFG at large guidance scales.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑