机器学习中光学图像数据集漂移控制的数据模型
Data Models for Dataset Drift Controls in Machine Learning With Optical Images
AI总结：
本研究提出将传统机器学习与物理光学结合，构建显式可微的数据模型，以控制图像数据集漂移对模型性能的影响，并应用于漂移合成、取证和优化。
摘要：
相机图像在机器学习研究中无处不在。它们在提供涵盖医学和环境调查的重要服务方面也发挥着核心作用。然而，由于鲁棒性问题，机器学习模型在这些领域的应用一直受到限制。一个主要的失效模式是由于训练数据与部署数据之间的差异导致的性能下降。虽然有方法可以前瞻性地验证机器学习模型对此类数据集漂移的鲁棒性，但现有方法并未考虑主要关注对象——数据——的显式模型。这限制了我们在物理精确的方式下研究和理解数据生成与下游机器学习模型性能之间关系的能力。在本研究中，我们展示了如何通过将传统机器学习与物理光学相结合，获得显式且可微的数据模型，从而克服这一限制。我们展示了如何为图像数据构建此类数据模型，并利用它们来控制与数据集漂移相关的下游机器学习模型性能。研究结果被提炼为三个应用。首先，漂移合成能够实现物理上忠实的漂移测试用例的受控生成，以支持模型选择和有针对性的泛化。其次，机器学习任务模型与数据模型之间的梯度连接允许对任务模型对数据生成变化的敏感性进行高级、精确的公差分析。这些漂移取证可用于精确指定任务模型可以运行的合格数据环境。第三，漂移优化开辟了创建有助于任务模型更好更快学习的漂移的可能性，从而有效地优化数据生成过程本身。访问开放代码和数据集的指南可在 https://github.com/aiaudit-org/raw2logit 获取。
英文摘要：
Camera images are ubiquitous in machine learning research. They also play a central role in the delivery of important services spanning medicine and environmental surveying. However, the application of machine learning models in these domains has been limited because of robustness concerns. A primary failure mode are performance drops due to differences between the training and deployment data. While there are methods to prospectively validate the robustness of machine learning models to such dataset drifts, existing approaches do not account for explicit models of the primary object of interest: the data. This limits our ability to study and understand the relationship between data generation and downstream machine learning model performance in a physically accurate manner. In this study, we demonstrate how to overcome this limitation by pairing traditional machine learning with physical optics to obtain explicit and differentiable data models. We demonstrate how such data models can be constructed for image data and used to control downstream machine learning model performance related to dataset drift. The findings are distilled into three applications. First, drift synthesis enables the controlled generation of physically faithful drift test cases to power model selection and targeted generalization. Second, the gradient connection between machine learning task model and data model allows advanced, precise tolerancing of task model sensitivity to changes in the data generation. These drift forensics can be used to precisely specify the acceptable data environments in which a task model may be run. Third, drift optimization opens up the possibility to create drifts that can help the task model learn better faster, effectively optimizing the data generating process itself. A guide to access the open code and datasets is available at https://github.com/aiaudit-org/raw2logit.
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。
