Time Series Anomaly Detection (TSAD) is essential for uncovering rare and potentially harmful events in unlabeled time series data. Existing methods are highly dependent on clean, high-quality inputs, making them susceptible to noise and real-world imperfections. Additionally, intricate temporal relationships in time series data are often inadequately captured in traditional 1D representations, leading to suboptimal modeling of dependencies. We introduce VISTA, a training-free, unsupervised TSAD algorithm designed to overcome these challenges. VISTA features three core modules: 1) Time Series Decomposition using Seasonal and Trend Decomposition via Loess (STL) to decompose noisy time series into trend, seasonal, and residual components; 2) Temporal Self-Attention, which transforms 1D time series into 2D temporal correlation matrices for richer dependency modeling and anomaly detection; and 3) Multivariate Temporal Aggregation, which uses a pretrained feature extractor to integrate cross-variable information into a unified, memory-efficient representation. VISTA's training-free approach enables rapid deployment and easy hyperparameter tuning, making it suitable for industrial applications. It achieves state-of-the-art performance on five multivariate TSAD benchmarks.
View on arXiv@article{chin2025_2504.02498,
title={ VISTA: Unsupervised 2D Temporal Dependency Representations for Time Series Anomaly Detection },
author={ Sinchee Chin and Fan Zhang and Xiaochen Yang and Jing-Hao Xue and Wenming Yang and Peng Jia and Guijin Wang and Luo Yingqun },
journal={arXiv preprint arXiv:2504.02498},
year={ 2025 }
}