UNSURE：基于未知噪声水平和Stein无偏风险估计的自监督学习
UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate
AI总结：
针对图像重建自监督学习中SURE类方法需已知噪声水平、Noise2Self类方法次优的问题，提出无需噪声水平知识的UNSURE方法，理论刻画表达性-鲁棒性权衡，实验表明其在多种图像逆问题上优于现有自监督方法。
摘要：
近年来，许多用于图像重建的自监督学习方法被提出，它们可仅从含噪数据中学习，无需真实参考。现有方法大多分为两类：i) Stein无偏风险估计（SURE）及类似方法，假设完全知晓噪声分布；ii) Noise2Self及类似交叉验证方法，仅需关于噪声分布的极少量知识。第一类方法往往不实用，因为现实应用中噪声水平常未知；第二类方法与监督学习相比通常不够最优。本文提出一个理论框架刻画这种表达性-鲁棒性权衡，并基于SURE提出新方法，与标准SURE不同，该方法无需知晓噪声水平。通过一系列实验，我们表明所提估计器在多种图像逆问题上优于其他现有自监督方法。
英文摘要：
Recently, many self-supervised learning methods for image reconstruction have been proposed that can learn from noisy data alone, bypassing the need for ground-truth references. Most existing methods cluster around two classes: i) Stein's Unbiased Risk Estimate (SURE) and similar approaches that assume full knowledge of the noise distribution, and ii) Noise2Self and similar cross-validation methods that require very mild knowledge about the noise distribution. The first class of methods tends to be impractical, as the noise level is often unknown in real-world applications, and the second class is often suboptimal compared to supervised learning. In this paper, we provide a theoretical framework that characterizes this expressivity-robustness trade-off and propose a new approach based on SURE, but unlike the standard SURE, does not require knowledge about the noise level. Throughout a series of experiments, we show that the proposed estimator outperforms other existing self-supervised methods on various imaging inverse problems.
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。
