cs.LGOct 29, 2026

Don't Just Impute, Detect: Task-Aware Diffusion Pipelines for Edge Anomaly Detection

Authors: Jeongsu Park, Taehyeon Yun, Geonwoo Kim, Yuji Lim, Moohong Min

Organizations: Sungkyunkwan University, Seoul, Republic of Korea

Abstract

Industrial Internet of Things (IIoT) edge pipelines routinely lose contiguous blocks of multi-sensor data to network dropouts and hardware faults. The standard remedy is a disjointed "impute-then-detect" pipeline whose imputer is trained only for Mean Squared Error (MSE). Such an imputer fills a missing block with the most probable normal pattern: a partially observed anomaly is smoothed back toward normality, and boundary artifacts on normal data raise false alarms. We call this imputation bias and propose the Task-Aware Diffusion Refiner (TADR), a conditional diffusion refiner trained against the loss landscape of a frozen downstream detector. Because back-propagating through the sampling trajectory is intractable, the task-aware terms act on the one-step clean-window estimate that the noise prediction already yields, so training costs no more than plain diffusion training. Under strict Point-to-Point evaluation over five seeds with paired significance tests, TADR raises F1 by 0.3380.338 over the unrefined detector on SMD (p=0.0015p = 0.0015), and the anomaly enhancement objective alone contributes 0.4630.463 in ablation. We also characterise when the method helps: the gain tracks the continuous, mutually redundant channels available and the anomaly evidence the outage removes, and it is absent on telemetry datasets dominated by one-hot command channels and on PSM. At ten sampling steps TADR runs in 41.441.4 ms per window on a single CPU core, sustaining about 2424 concurrent 1 Hz streams from a 4.034.03 MB model. Code and per-seed results are available at https://github.com/int-park422/TADR.

Figures & tables

Explore similar work

CardsList
  1. One-Step Diffusion with Inverse Residual Fields for Unsupervised Industrial Anomaly Detection

    Apr 20, 2026Boan Zhang, Wen Li, Guanhua Yu +3Industrial Anomaly DetectionUnsupervised Anomaly Detection

  2. Diffuse to Detect: Generative Diffusion Models for Unsupervised IC Anomaly Detection

    May 26, 2026Yuxuan Yin, Chen He, Todd Jacobs +4Semiconductor ManufacturingIndustrial Anomaly Detection