# 重返修复：用于时间序列异常检测的极简去噪网络

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-04-19 08:00
- AIHOT 链接：https://aihot.virxact.com/items/cmo86vj4q0451slmlyvxqanql
- 原文链接：https://arxiv.org/abs/2604.17388

## AI 摘要

研究团队提出名为 JuRe 的极简去噪网络，仅使用单个深度可分离卷积残差块（隐藏维度128），通过修复损坏的时间序列窗口进行训练，并以无参数结构差异函数评分。该模型在 TSB-AD 多变量基准（180序列，17数据集）和 UCR 单变量档案（250序列）均获 AUC-PR 第二名（分别为0.404和0.198），领先所有神经基线。消融实验显示，训练时损坏机制是性能主导因素，移除后 AUC-PR 下降0.047，证实去噪目标而非网络容量决定检测质量。

## 正文

We introduce JuRe (Just Repair), a minimal denoising network for time series anomaly detection that exposes a central finding: architectural complexity is unnecessary when the training objective correctly implements the manifold-projection principle. JuRe consists of a single depthwise-separable convolutional residual block with hidden dimension 128, trained to repair corrupted time series windows and scored at inference by a fixed, parameter-free structural discrepancy function. Despite using no attention, no latent variable, and no adversarial component, JuRe ranks second on the TSB-AD multivariate benchmark (AUC-PR 0.404, 180 series, 17 datasets) and second on the UCR univariate archive by AUC-PR (0.198, 250 series), leading all neural baselines on AUC-PR and VUS-PR. Component ablation on TSB-AD identifies training-time corruption as the dominant factor (ΔAUC-PR = 0.047 on removal), confirming that the denoising objective, not network capacity, drives detection quality. Pairwise Wilcoxon signed-rank tests establish statistical significance against 21 of 25 baselines on TSB-AD. Code is available at the URL https://github.com/iis-esslingen/JuRe.