计算机视觉模型对常见扰动的鲁棒性综述
A Survey on the Robustness of Computer Vision Models against Common Corruptions
AI总结：
该综述梳理了提升计算机视觉模型抗常见扰动鲁棒性的三类方法，发布统一基准框架解决评估不一致问题，实验发现鲁棒性不随模型与数据规模必然提升，指出需开发高效利用有限数据的新型学习策略。
摘要：
计算机视觉模型的性能易受传感器误差或极端成像环境导致的输入图像意外变化影响，这类变化被称为常见扰动（common corruptions，例如噪声、模糊、光照变化）。这些扰动会显著降低模型在真实场景部署时的可靠性，但在测试模型泛化性和鲁棒性时却常被忽视。本综述全面梳理了提升计算机视觉模型抗常见扰动鲁棒性的各类方法，根据方法针对的模型组件与训练方式，将其分为数据增强、学习策略、网络组件三类。我们发布了一个统一基准框架CorruptionBenchCV（可在https://github.com/nis-research/CorruptionBenchCV获取），用于跨多个数据集比较鲁棒性表现，同时解决了现有文献中评估流程不一致的问题。我们的实验分析揭示了主流视觉骨干网络的基础扰动鲁棒性，发现扰动鲁棒性并不一定随模型规模和数据规模提升而增强；考虑到计算需求的增加，大模型的鲁棒性提升微乎其微。为实现具备泛化能力的鲁棒计算机视觉模型，我们认为需要开发能高效利用有限数据、减少不可靠学习行为的新型学习策略。
英文摘要：
The performance of computer vision models are susceptible to unexpected changes in input images caused by sensor errors or extreme imaging environments, known as common corruptions (e.g. noise, blur, illumination changes). These corruptions can significantly hinder the reliability of these models when deployed in real-world scenarios, yet they are often overlooked when testing model generalization and robustness. In this survey, we present a comprehensive overview of methods that improve the robustness of computer vision models against common corruptions. We categorize methods into three groups based on the model components and training methods they target: data augmentation, learning strategies, and network components. We release a unified benchmark framework (available at \url{https://github.com/nis-research/CorruptionBenchCV}) to compare robustness performance across several datasets, and we address the inconsistencies of evaluation practices in the literature. Our experimental analysis highlights the base corruption robustness of popular vision backbones, revealing that corruption robustness does not necessarily scale with model size and data size. Large models gain negligible robustness improvements, considering the increased computational requirements. To achieve generalizable and robust computer vision models, we foresee the need of developing new learning strategies that efficiently exploit limited data and mitigate unreliable learning behaviors.
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。
