用风格迁移的局部补丁替换图像区域，提升模型泛化能力。
Data Augmentation Through Random Style Replacement
- 随机选取图像区域，用风格迁移后的补丁替换
- 相比传统方法，收敛更快且准确率更高
- 适配多种风格迁移算法，易于集成到现有流程
本文提出一种新型数据增强方法，通过有选择地将图像子区域替换为风格迁移后的补丁，融合了风格增强与随机擦除的优势。首先对训练图像进行随机风格迁移，随后从迁移后的版本中提取补丁，替换原图中的随机区域。该方法可无缝兼容多种现有风格迁移算法，并能轻松嵌入各类数据增强流程。实验表明，采用此策略后训练过程更具鲁棒性，更难过拟合。对比实验显示，相较于以往风格增强方法，本方法在性能上表现更优，收敛速度更快。
原文摘要 · Abstract (English)
In this paper, we introduce a novel data augmentation technique that combines the advantages of style augmentation and random erasing by selectively replacing image subregions with style-transferred patches. Our approach first applies a random style transfer to training images, then randomly substitutes selected areas of these images with patches derived from the style-transferred versions. This method is able to seamlessly accommodate a wide range of existing style transfer algorithms and can be readily integrated into diverse data augmentation pipelines. By incorporating our strategy, the training process becomes more robust and less prone to overfitting. Comparative experiments demonstrate that, relative to previous style augmentation methods, our technique achieves superior performance and faster convergence.
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。