用扩散模型实现时间序列风格迁移，提升小样本场景下的异常检测效果。
DiffStyleTS: Diffusion Model for Style Transfer in Time Series
- 通过卷积编码器分离时序内容与风格，再用自监督注意力扩散过程重组。
- 在真实数据上验证了风格迁移有效性，并使小样本异常检测性能显著提升。
- 适合需要数据增强的工业故障检测、金融时序建模等场景。
风格迁移将一个信号的内容与另一个信号的风格相结合，支持数据增强和场景模拟，有助于机器学习模型在数据稀缺领域泛化。尽管视觉和语言领域已发展成熟，时间序列风格迁移方法仍较为有限。我们提出 DiffTSST，一种基于扩散的框架，通过卷积编码器将时序数据解耦为内容与风格表征，并利用自监督注意力扩散过程进行重组。推理时，编码器从两个不同序列中提取内容与风格，实现条件生成以完成风格迁移。我们通过定性与定量分析证明，DiffTSST 能有效实现风格迁移。进一步验证其实际价值：使用 DiffTSST 进行数据增强可显著提升数据稀缺环境下的异常检测性能。
原文摘要 · Abstract (English)
Style transfer combines the content of one signal with the style of another. It supports applications such as data augmentation and scenario simulation, helping machine learning models generalize in data-scarce domains. While well developed in vision and language, style transfer methods for time series data remain limited. We introduce DiffTSST, a diffusion-based framework that disentangles a time series into content and style representations via convolutional encoders and recombines them through a self-supervised attention-based diffusion process. At inference, encoders extract content and style from two distinct series, enabling conditional generation of novel samples to achieve style transfer. We demonstrate both qualitatively and quantitatively that DiffTSST achieves effective style transfer. We further validate its real-world utility by showing that data augmentation with DiffTSST improves anomaly detection in data-scarce regimes.
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。