# When Model Meets New Normals: Test-time Adaptation for Unsupervised Time-series Anomaly Detection

arXiv: https://arxiv.org/abs/2312.11976 · HTML: https://mlsanity.com/paper/2312.11976/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## Builds on (most cited first, 14 of 14)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https://mlsanity.com/paper/1802.03903/) (2018)
- [LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection](https://mlsanity.com/paper/1607.00148/) (2016)
- [A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder](https://mlsanity.com/paper/1711.00614/) (2017)
- [Generative Adversarial Active Learning for Unsupervised Outlier Detection](https://mlsanity.com/paper/1809.10816/) (2018)
- [TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks](https://mlsanity.com/paper/2009.07769/) (2020)
- [MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstruction](https://mlsanity.com/paper/2007.13559/) (2020)

## Built on by (most cited first, 17 of 17)

- [Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting](https://mlsanity.com/paper/2506.23424/) (2025)
- [PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection](https://mlsanity.com/paper/2401.09793/) (2024)
- [SimAD: A Simple Dissimilarity-based Approach for Time Series Anomaly Detection](https://mlsanity.com/paper/2405.11238/) (2024)
- [Test-Time Distillation for Continual Model Adaptation](https://mlsanity.com/paper/2506.02671/) (2025)
- [AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning](https://mlsanity.com/paper/2602.13807/) (2026)
- [Position: Universal Time Series Foundation Models Rest on a Category Error](https://mlsanity.com/paper/2602.05287/) (2026)
- [GDFlow: Anomaly Detection with NCDE-based Normalizing Flow for Advanced Driver Assistance System](https://mlsanity.com/paper/2409.05346/) (2024)
- [CCE: Confidence-Consistency Evaluation for Time Series Anomaly Detection](https://mlsanity.com/paper/2509.01098/) (2025)
- [naPINN: Noise-Adaptive Physics-Informed Neural Networks for Recovering Physics from Corrupted Measurement](https://mlsanity.com/paper/2602.02547/) (2026)
- [Adapt Data to Model: Adaptive Transformation Optimization for Domain-shared Time Series Foundation Models](https://mlsanity.com/paper/2603.00629/) (2026)
- [COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection](https://mlsanity.com/paper/2602.01635/) (2026)
- [Catching Every Ripple: Enhanced Anomaly Awareness via Dynamic Concept Adaptation](https://mlsanity.com/paper/2604.14726/) (2026)
- [Just Repair: A Minimal Denoising Network for Time Series Anomaly Detection](https://mlsanity.com/paper/2604.17388/) (2026)
- [When Normality Shifts: Risk-Aware Test-Time Adaptation for Unsupervised Tabular Anomaly Detection](https://mlsanity.com/paper/2605.10242/) (2026)
- [Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection](https://mlsanity.com/paper/2605.26193/) (2026)
- [Efficient Regression Models for Scan Statistics](https://mlsanity.com/paper/2608.22201/) (2026)
- [Supervision Recovery for Time Series Anomaly Detection via Context-Anchored Pairing](https://mlsanity.com/paper/2609.33610/) (2026)

## Abstract (arXiv)

Time-series anomaly detection deals with the problem of detecting anomalous timesteps by learning normality from the sequence of observations. However, the concept of normality evolves over time, leading to a "new normal problem", where the distribution of normality can be changed due to the distribution shifts between training and test data. This paper highlights the prevalence of the new normal problem in unsupervised time-series anomaly detection studies. To tackle this issue, we propose a simple yet effective test-time adaptation strategy based on trend estimation and a self-supervised approach to learning new normalities during inference. Extensive experiments on real-world benchmarks demonstrate that incorporating the proposed strategy into the anomaly detector consistently improves the model's performance compared to the baselines, leading to robustness to the distribution shifts.