[2603.26842] VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection

Computer Science > Machine Learning arXiv:2603.26842 (cs) [Submitted on 27 Mar 2026] Title:VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection Authors:PengYu Chen, Shang Wan, Xiaohou Shi, Yuan Chang, Yan Sun, Sajal K. Das View a PDF of the paper titled VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection, by PengYu Chen and 5 other authors View PDF HTML (experimental) Abstract:Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems. Existing methods require training one specific model for each dataset, which exhibits limited generalization capability across different target datasets, hindering anomaly detection performance in various scenarios with scarce training data. To address this limitation, foundation models have emerged as a promising direction. However, existing approaches either repurpose large language models (LLMs) or construct largescale time series datasets to develop general anomaly detection foundation models, and still face challenges caused by severe cross-modal gaps or in-domain heterogeneity. In this paper, we investigate the applicability of large-scale vision models to TSAD. Specifically, we adapt a visual Masked Autoencoder (MAE) pretrained on ImageNet to the TSAD task. However, directly transferring MAE to TSAD introduces two key challenges: overgeneralization and limited local perception. To address these ...