提出抗异常值的扩散模型求解器，提升逆问题重建稳定性。
Outlier-Robust Diffusion Solvers for Inverse Problems
- 通过噪声估计预处理测量数据，减轻异常影响。
- 采用基于Huber损失的加权最小二乘法，有效抑制异常值干扰。
- 结合共轭梯度法实现高效优化，避免学习率调参难题。
基于扩散模型（DMs）求解逆问题（IPs）近期取得显著进展，但通常对异常值敏感，而真实测量中异常值普遍存在。本文首先通过显式噪声估计对测量数据进行预处理以缓解噪声影响；随后，基于Huber损失构建迭代重加权最小二乘目标函数来应对异常值；进而提出一种利用梯度下降近似求解该鲁棒目标的方法。为避免梯度下降中精细调整学习率的困扰，进一步引入共轭梯度法并设计高效更新策略。在多种图像数据集上针对线性和非线性任务，在不同条件下开展的大量实验表明，所提方法对异常值具有强鲁棒性，且多数情况下优于当前主流的基于扩散模型的方法。代码已开源：https://github.com/StarNextDay/Robust-DAPS.git。
原文摘要 · Abstract (English)
Methods based on diffusion models (DMs) for solving inverse problems (IPs) have recently achieved remarkable performance. However, DM-based methods typically struggle against outliers, which are common in real-world measurements. In this work, to tackle IPs with outliers, we first refine the measurement via explicit noise estimation to mitigate the effect of noise. Subsequently, we formulate an iteratively reweighted least squares objective based on the Huber loss to address the outliers. We propose a method utilizing gradient descent to approximately solve the corresponding optimization problem for the robust objective. To avoid delicate tuning of the learning rate required by the gradient descent method, we further employ the conjugate gradient method with an efficient strategy for updating. Extensive experiments on multiple image datasets for linear and nonlinear tasks under various conditions demonstrate that our proposed methods exhibit robustness to outliers and outperform recent DM-based methods in most cases. The code is available at https://github.com/StarNextDay/Robust-DAPS.git.
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。