Weakly Supervised Temporal Anomaly Segmentation with Dynamic Time Warping
Authors:
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7335-7344
Abstract
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.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- Unsupervised real-time anomaly detection for streaming dataNeurocomputing, 2017
- Time series classification from scratch with deep neural networks: A strong baseline2017
- Deep Residual Learning for Image Recognition2016
- Learning Temporal Regularity in Video Sequences2016
- Fraud detection system: A surveyJournal of Network and Computer Applications, 2016
- Fully convolutional networks for semantic segmentation2015
- The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced DatasetsPLOS ONE, 2015
- Anomaly detectionACM Computing Surveys, 2009
- Robust Real-Time Unusual Event Detection using Multiple Fixed-Location MonitorsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Dynamic programming algorithm optimization for spoken word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1978