让基础流匹配模型在逆问题中更好用，尤其适合样本少的科学场景。
Saving Foundation Flow-Matching Priors for Inverse Problems
- 用动态启动+高斯正则，让基础模型适配具体逆问题。
- 在图像修复和少量样本科学任务上表现优于专用模型。
- 适合数据稀缺、难训练的科学逆问题应用。
基础流匹配（FM）模型有望成为解决逆问题（IPs）的通用先验，但当前性能仍不及领域特定或未训练的先验。我们提出FMPlug——一种即插即用框架，重新定义了基础FM在逆问题中的使用方式。FMPlug结合实例引导的时变热启动策略与尖锐高斯性正则化，在引入问题特异性指导的同时保持高斯结构。评估涵盖简单图像修复任务及仅含少量相似样本的科学逆问题——这些场景因数据采集和模型训练成本过高，难以发展领域专用生成模型。实验结果表明，FMPlug显著优于现有方法。整体而言，该框架使基础FM模型成为可复用、实用的逆问题先验，尤其适用于小样本科学场景。更多信息见 https://sun-umn.github.io/xm-plug/。
原文摘要 · Abstract (English)
Foundation flow-matching (FM) models promise universal priors for solving inverse problems (IPs); yet today, they trail behind domain-specific and even untrained priors. \emph{How can we unlock their potential?} We introduce FMPlug, a plug-in framework that redefines how foundation FMs are used in IPs. FMPlug combines an instance-guided, time-dependent warm-start strategy with sharp Gaussianity regularization, adding problem-specific guidance while preserving the Gaussian structures. For evaluation, we consider both simple image restoration tasks and scientific IPs with a few similar samples -- where the prohibitive cost of data collection and model training hinders the development of domain-specific generative models. Our superior experimental results confirm the effectiveness of FMPlug. Overall, FMPlug paves the way for making foundation FM models practical, reusable priors for IPs, especially scientific ones with few similar samples. More details are available at https://sun-umn.github.io/xm-plug/ .
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。