Back to Repair: A Minimal Denoising Network\ for Time Series Anomaly Detection
For time series anomaly detection, JuRe shows that a simple denoising objective can match or exceed complex neural architectures, challenging the need for attention or adversarial components.
JuRe, a minimal denoising network with a single convolutional block, achieves second-best AUC-PR on TSB-AD multivariate benchmark (0.404) and UCR univariate archive (0.198), outperforming all neural baselines. Ablation studies confirm that the denoising objective, not architectural complexity, drives performance.
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 ($Δ$AUC-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.