2025/07/29 by Aitor Sánchez-Ferrera, Sánchez-Ferrera, Aitor, Usue Mori +6
Computer Science · #Anomaly Detection Techniques and Applications #Anomaly detection #Generalization #Human Pose and Action Recognition #Limiting #Proxy (statistics) #Range (aeronautics) #Series (stratigraphy) #Time Series Analysis and Forecasting #Time series
paper · pdf · open access · doi:10.1016/j.neunet.2026.109375
published in Neural Networks 205(Pt A), 109375 (Elsevier BV)
openalex created_date 2025/10/10 · openalex publication_date 2026/07/13 · openalex updated_date 2026/08/05
Time series anomaly detection plays a critical role in a wide range of real-world applications. Among unsupervised approaches, self-supervised learning has gained traction for modeling normal behavior without the need of labeled data. However, many existing methods rely on a single proxy task, limiting their ability to capture meaningful patterns in normal data. Moreover, they often depend on handcrafted transformations tailored to specific domains, hindering their generalization across diverse problems. To address these limitations, we introduce NeuCoReClass AD, a self-supervised multi-task time series anomaly detection framework that combines contrastive, reconstruction, and classification proxy tasks. Our method employs neural transformation learning to generate augmented views that are informative, diverse, and coherent, without requiring domain-specific knowledge. We evaluate NeuCoReClass AD across a wide range of benchmarks, demonstrating that it consistently outperforms both classical baselines and most deep-learning alternatives. Furthermore, it enables the characterization of distinct anomaly profiles in a fully unsupervised manner. Our code is publicly available at https://github.com/Aitorzan3/NeuCoReClass-AD.