arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.08352cs.LGcs.AIcs.CVcs.NE
收藏

使用自动化机器学习进行数据增强:方法及与经典数据增强方法的性能比较

Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods

Cape Coast Technical University(海岸角理工大学);University of Mines and Technology(矿业与技术大学)

Alhassan Mumuni, Fuseini Mumuni

AI总结:

本文全面调研了基于AutoML的数据增强技术,涵盖数据操作、集成与合成方法,并重点探讨了图像数据增强的搜索空间设计、超参数优化和模型评估,实验证明AutoML方法优于经典常规方法。

摘要:

数据增强可以说是最常用且最重要的正则化技术,通常用于提升机器学习模型的泛化性能。它主要涉及应用适当的数据转换操作,以创建具有所需属性的新数据样本。尽管其非常有效,但由于手动创建和测试不同的候选增强及其超参数的过程十分耗时,该过程往往充满挑战。最先进的方法越来越依赖于自动化机器学习(AutoML)原理。本工作对基于AutoML的数据增强技术进行了全面调查。我们讨论了使用AutoML完成数据增强的各种方法,包括数据操作、数据集成和数据合成技术。本工作的重点是图像数据增强方法。尽管如此,我们也涵盖了其他数据模态,特别是在所讨论的特定数据增强技术更适合这些其他模态的情况下。例如,由于自动化数据集成方法更适合表格数据,我们在数据集成方法的讨论中涵盖了表格数据。本工作还对完成图像数据增强过程各个主要子任务的技术进行了广泛讨论:搜索空间设计、超参数优化和模型评估。最后,我们对自动化数据增强技术与基于经典增强方法的最先进技术的性能进行了广泛的比较和分析。结果表明,用于数据增强的AutoML方法目前优于基于常规方法的最先进技术。

英文摘要:

Data augmentation is arguably the most important regularization technique commonly used to improve generalization performance of machine learning models. It primarily involves the application of appropriate data transformation operations to create new data samples with desired properties. Despite its effectiveness, the process is often challenging because of the time-consuming trial and error procedures for creating and testing different candidate augmentations and their hyperparameters manually. State-of-the-art approaches are increasingly relying on automated machine learning (AutoML) principles. This work presents a comprehensive survey of AutoML-based data augmentation techniques. We discuss various approaches for accomplishing data augmentation with AutoML, including data manipulation, data integration and data synthesis techniques. The focus of this work is on image data augmentation methods. Nonetheless, we cover other data modalities, especially in cases where the specific data augmentations techniques being discussed are more suitable for these other modalities. For instance, since automated data integration methods are more suitable for tabular data, we cover tabular data in the discussion of data integration methods. The work also presents extensive discussion of techniques for accomplishing each of the major subtasks of the image data augmentation process: search space design, hyperparameter optimization and model evaluation. Finally, we carried out an extensive comparison and analysis of the performance of automated data augmentation techniques and state-of-the-art methods based on classical augmentation approaches. The results show that AutoML methods for data augmentation currently outperform state-of-the-art techniques based on conventional approaches.

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。

↑