揭示数据增强提升泛化能力的两大机制，统一解释主流方法原理。
Towards Understanding Why Data Augmentation Improves Generalization
- 提出统一理论框架，从特征移除与混合两方面解析增强效果。
- 实验验证：特征移除降低对单一特征依赖，混合提升鲁棒性。
- 适合想理解数据增强内在机理的研究者和工程师参考。
数据增强是深度学习中提升模型泛化能力的核心技术，从随机裁剪、色彩抖动到CutOut、Mixup、CutMix等先进方法均取得显著成效。然而，其提升泛化的内在机制仍不清晰，现有理论分析多局限于单个方法，缺乏统一解释。本文提出一个统一的理论框架，阐明数据增强通过两个关键效应改善泛化：部分语义特征移除与特征混合。前者减少模型对特定特征的依赖，促进多样化特征学习；后者通过缩小原始语义特征并引入噪声，增加训练复杂度，促使模型习得更鲁棒的特征。先进的方法如CutMix同时整合两种效应，获得互补优势。理论分析得到实验结果支持，验证了该统一视角的有效性。
原文摘要 · Abstract (English)
Data augmentation is a cornerstone technique in deep learning, widely used to improve model generalization. Traditional methods like random cropping and color jittering, as well as advanced techniques such as CutOut, Mixup, and CutMix, have achieved notable success across various domains. However, the mechanisms by which data augmentation improves generalization remain poorly understood, and existing theoretical analyses typically focus on individual techniques without a unified explanation. In this work, we present a unified theoretical framework that elucidates how data augmentation enhances generalization through two key effects: partial semantic feature removal and feature mixing. Partial semantic feature removal reduces the model's reliance on individual feature, promoting diverse feature learning and better generalization. Feature mixing, by scaling down original semantic features and introducing noise, increases training complexity, driving the model to develop more robust features. Advanced methods like CutMix integrate both effects, achieving complementary benefits. Our theoretical insights are further supported by experimental results, validating the effectiveness of this unified perspective.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。