Weakly Supervised Temporal Anomaly Segmentation with Dynamic Time Warping
This addresses the challenge of precise anomaly segmentation in temporal data for applications like surveillance or monitoring, but it is incremental as it builds on weakly supervised methods.
The paper tackles the problem of localizing anomalous temporal segments in data using only instance-level anomaly labels, and the result is that WETAS outperforms baselines in anomaly localization and provides more informative results than point-level detection methods.
Most recent studies on detecting and localizing temporal anomalies have mainly employed deep neural networks to learn the normal patterns of temporal data in an unsupervised manner. Unlike them, the goal of our work is to fully utilize instance-level (or weak) anomaly labels, which only indicate whether any anomalous events occurred or not in each instance of temporal data. In this paper, we present WETAS, a novel framework that effectively identifies anomalous temporal segments (i.e., consecutive time points) in an input instance. WETAS learns discriminative features from the instance-level labels so that it infers the sequential order of normal and anomalous segments within each instance, which can be used as a rough segmentation mask. Based on the dynamic time warping (DTW) alignment between the input instance and its segmentation mask, WETAS obtains the result of temporal segmentation, and simultaneously, it further enhances itself by using the mask as additional supervision. Our experiments show that WETAS considerably outperforms other baselines in terms of the localization of temporal anomalies, and also it provides more informative results than point-level detection methods.