分离生成模型中固有模糊与估计不确定性，提升医学成像等反问题的可信度。
Separating Intrinsic Ambiguity from Estimation Uncertainty in Deep Generative Models for Linear Inverse Problems
- 通过级联结构分解后验不确定性，分离出由正向算子导致的固有模糊。
- 在加速MRI和脑电图源成像中验证了该方法能揭示模型隐藏失败模式。
- 适合关注生成模型可靠性、需可解释性评估的医疗与科学计算研究者。
深度生成模型近年来被用于反问题中的后验推断，涵盖医学成像与科学发现等高风险场景，其中预测的不确定性与预测本身同样重要。然而，后验不确定性难以解释，因其混合了正向算子固有的模糊性与推断过程中传播的不确定性。本文提出一种后验不确定性的结构分解方法，可分离出固有模糊性。级联形式使该模糊性可被校准分析，支持定性诊断与基于仿真的校准测试，揭示仅凭重建质量无法发现的模型失效模式。首先在具有解析后验结构的高斯示例上验证方法，随后在加速磁共振成像（MRI）上展示分解效果，并将校准诊断应用于脑电图（EEG）源成像。
原文摘要 · Abstract (English)
Recently, deep generative models have been used for posterior inference in inverse problems, including high-stakes applications in medical imaging and scientific discovery, where the uncertainty of a prediction can matter as much as the prediction itself. However, posterior uncertainty is difficult to interpret because it can mix ambiguity inherent to the forward operator with uncertainty propagated through inference. We introduce a structural decomposition of posterior uncertainty that isolates intrinsic ambiguity. A cascade formulation makes this ambiguity accessible for calibration analysis, enabling qualitative diagnostics and simulation-based calibration tests that reveal failure modes that remain hidden when models are selected by reconstruction quality alone. We first validate the approach on a Gaussian example with analytical posterior structure, then illustrate the decomposition on accelerated magnetic resonance imaging (MRI), and finally apply the calibration diagnostics to electroencephalography (EEG) source imaging.
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。