给生成模型加不确定性评估，让好样本更可靠，差样本更少。
Flow Matching with Uncertainty Quantification and Guidance
- 在流匹配中同时预测速度与不确定性，实现每张图的可靠性评估
- 不确定性信号与样本质量相关性高于基线方法，提升生成质量
- 适合需要可信生成结果的应用，如医疗图像生成
尽管基于采样的生成模型（如流匹配）取得了显著成功，但仍可能产生质量不一或退化的样本。为评估样本可靠性并生成更高质量输出，我们提出不确定性感知流匹配（UA-Flow），这是对流匹配的轻量级扩展，可同时预测速度场和异方差不确定性。UA-Flow通过传播速度不确定性来估计每个样本的不确定性。这些不确定性估计作为个体样本的可靠性信号，并进一步用于实现不确定性感知的分类器引导和无分类器引导。在图像生成任务上的实验表明，UA-Flow产生的不确定性信号与样本保真度的相关性高于基线方法，且基于不确定性的采样进一步提升了生成质量。
原文摘要 · Abstract (English)
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 generate higher-quality outputs, 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 per-sample uncertainty by propagating velocity uncertainty through the flow dynamics. These uncertainty estimates act as a reliability signal for individual samples, and we further use them to steer generation via uncertainty-aware classifier guidance and classifier-free guidance. Experiments on image generation show that UA-Flow produces uncertainty signals more highly correlated with sample fidelity than baseline methods, and that uncertainty-guided sampling further improves generation quality.
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。