Non-adversarial robustness, also known as natural robustness, is a property of deep learning models that enables them to maintain performance even when faced with distribution shifts caused by natural variations in data. However, achieving this property is challenging because it is difficult to predict in advance the types of distribution shifts that may occur. To address this challenge, researchers have proposed various approaches, some of which anticipate potential distribution shifts, while others utilize knowledge about the shifts that have already occurred to enhance model generalizability. In this paper, we present a brief overview of the most recent techniques for improving the robustness of computer vision methods, as well as a summary of commonly used robustness benchmark datasets for evaluating the model's performance under data distribution shifts. Finally, we examine the strengths and limitations of the approaches reviewed and identify general trends in deep learning robustness improvement for computer vision.

翻译：非对抗鲁棒性（也称为自然鲁棒性）是深度学习模型的一种属性，使其即使面对由数据自然变化引起的分布偏移时也能保持性能。然而，实现这一属性具有挑战性，因为难以预先预测可能出现的分布偏移类型。为解决这一挑战，研究者提出了多种方法，其中部分方法预判潜在的分布偏移，另一些则利用已发生的偏移知识来增强模型泛化能力。本文简要概述了提升计算机视觉方法鲁棒性的最新技术，以及用于评估模型在数据分布偏移下性能的常用鲁棒性基准数据集。最后，我们审视了所综述方法的优势与局限，并归纳了计算机视觉深度学习鲁棒性改进的总体趋势。