VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection

arXiv:2602.16681v2 Announce Type: replace Abstract: Time-series anomaly detection (TSAD) requires identifying both immediate Point Anomalies and long-range Context Anomalies. However, existing foundation models face a fundamental trade-off: 1D temporal models provide fine-grained pointwise localization but lack a global contextual perspective, while 2D vision-based models capture global patterns but suffer from information bottlenecks due to a lack of temporal alignment and coarse-grained pointwise detection. To resolve this dilemma, we propose VETime, the first TSAD framework that unifies temporal and visual modalities through fine-grained visual-temporal alignment and dynamic fusion. VETime introduces a Reversible Image Conversion and a Patch-Level Temporal Alignment module to establish a shared visual-temporal timeline, preserving discriminative details while maintaining temporal sensitivity. Furthermore, we design an Anomaly Window Contrastive Learning mechanism and a Task-Adaptive Multi-Modal Fusion to adaptively integrate the complementary perceptual strengths of both modalities. Extensive experiments demonstrate that VETime significantly outperforms state-of-the-art models in zero-shot scenarios, achieving superior localization precision with lower computational overhead than current vision-based approaches. Code available at: https://github.com/yyyangcoder/VETime .

Related

• Unlocking Pretrained Vision Transformers for Time Series Classification
• Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection
• CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection
• EntroAD: Structural Entropy-Guided Prompt Adaptation for Zero-Shot Anomaly Detection
• VFAD: Variational Semantic Prompting Meets Frequency-Adaptive Representation Learning for Zero-Shot Anomaly Detection

Source: arXiv cs.CV | 2026-10-14