Data augmentation (DA) is indispensable in modern machine learning and deep neural networks. The basic idea of DA is to construct new training data to improve the model’s generalization by adding slightly disturbed versions of existing data or synthesizing new data. This survey comprehensively reviews a crucial subset of DA techniques, namely Mix-based Data Augmentation (MixDA), which generates novel samples by combining multiple examples. In contrast to traditional DA approaches that operate on single samples or entire datasets, MixDA stands out due to its effectiveness, simplicity, computational efficiency, theoretical foundation, and broad applicability. We begin by introducing a novel taxonomy that categorizes MixDA into Mixup-based, Cutmix-based, and mixture approaches based on a hierarchical perspective of the data mixing operation. Subsequently, we provide an in-depth review of various MixDA techniques, focusing on their underlying motivations. Owing to its versatility, MixDA has penetrated a wide range of applications, which we also thoroughly investigate in this survey. Moreover, we delve into the underlying mechanisms of MixDA’s effectiveness by examining its impact on model generalization and calibration while providing insights into the model’s behavior by analyzing the inherent properties of MixDA. Finally, we recapitulate the critical findings and fundamental challenges of current MixDA studies while outlining the potential directions for future works. Different from previous related surveys that focus on DA approaches in specific domains (e.g., computer vision and natural language processing) or only review a limited subset of MixDA studies, we are the first to provide a systematical survey of MixDA, covering its taxonomy, methodology, application, and explainability. Furthermore, we provide promising directions for researchers interested in this exciting area.

中文翻译：

---

基于混合的数据增强调查：分类、方法、应用和可解释性


数据增强 （DA） 在现代机器学习和深度神经网络中是必不可少的。DA 的基本思想是通过添加现有数据的略微干扰版本或合成新数据来构建新的训练数据以提高模型的泛化程度。本调查全面回顾了 DA 技术的一个重要子集，即基于混合的数据增强 （MixDA），它通过组合多个示例来生成新的样本。与对单个样本或整个数据集进行操作的传统 DA 方法相比，MixDA 因其有效性、简单性、计算效率、理论基础和广泛的适用性而脱颖而出。我们首先介绍一种新的分类法，根据数据混合操作的分层视角，将 MixDA 分为基于 Mixup、基于 Cutmix 和混合方法。随后，我们对各种 MixDA 技术进行了深入回顾，重点关注其潜在动机。由于其多功能性，MixDA 已经渗透到广泛的应用程序中，我们在本次调查中也对此进行了深入调查。此外，我们通过检查其对模型泛化和校准的影响来深入研究 MixDA 有效性的底层机制，同时通过分析 MixDA 的固有属性来深入了解模型的行为。最后，我们概括了当前 MixDA 研究的关键发现和基本挑战，同时概述了未来工作的潜在方向。与以往侧重于特定领域的 DA 方法的相关调查不同（例如、计算机视觉和自然语言处理）或仅回顾 MixDA 研究的有限子集，我们是第一个提供 MixDA 系统调查的公司，涵盖其分类、方法、应用和可解释性。此外，我们为对这个令人兴奋的领域感兴趣的研究人员提供了有前途的方向。