AI 中文总结
提出MSCAD，一种基于并行自编码器分支和双向跨尺度注意力的半监督时间序列异常检测框架，在TSB-AD基准上显著超越现有方法。
AI 中文摘要
时间序列异常检测（TSAD）在医疗保健、金融、工业监控等领域中扮演着至关重要的角色。在这些场景内部及之间，异常跨越了截然不同的时间尺度，从亚秒级点尖峰到数小时的漂移模式。然而，大多数现有的TSAD方法都致力于单一的时间粒度，而多尺度设计要么孤立地分析不同尺度，要么受限于预定义的从粗到细的层次结构，这两者都未能充分捕捉多尺度交互。为解决这一局限，我们提出了多尺度自编码器与跨尺度注意力用于TSAD（MSCAD），这是一个简单而强大的半监督TSAD框架，基于对应不同补丁大小的并行自编码器分支。一组对称的双向跨尺度注意力块使得每对尺度都能在重建前交换信息，而不允许任何单一尺度享有特权。在全面的TSB-AD基准（40个数据集，530个序列）上，MSCAD在多个指标上相对于50个基线取得了显著的性能提升，在单变量分割上VUS-PR为0.57（+9.6%），在多变量分割上为0.47（+9.3%），相比最先进方法有所提高。
英文摘要
Time series anomaly detection (TSAD) plays a crucial role in healthcare, finance, industrial monitoring, and other sectors. Within and between these settings, anomalies span vastly different temporal scales, from sub-second point spikes to multi-hour drift patterns. However, most existing TSAD methods commit to a single temporal granularity, and multi-scale designs either analyze different scales in isolation or are constrained to a predefined coarse-to-fine hierarchy, both failing to sufficiently capture multi-scale interactions. To resolve this limitation, we propose Multi-Scale Autoencoder with Cross-Scale Attention for TSAD (MSCAD), a simple yet powerful semi-supervised TSAD framework founded on parallel autoencoder branches corresponding to different patch sizes. A stack of symmetric bidirectional cross-scale attention blocks enables every pair of scales to exchange information before reconstruction without allowing any single scale to be privileged. On the comprehensive TSB-AD benchmark (40 datasets, 530 series), MSCAD achieves large performance gains against 50 baselines across multiple metrics, with VUS-PR of 0.57(+9.6%) on the univariate split and 0.47(+9.3%) on the multivariate split compared to the state-of-the-art.
