mlsanityData to 14 Oct 2026

A Reliable Framework for Human-in-the-Loop Anomaly Detection in Time Series

arXiv 2405.03234 ↗First posted 6 May 2024cs.HC cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Time series anomaly detection is a critical machine learning task for numerous applications, such as finance, healthcare, and industrial systems. However, even high-performing models may exhibit potential issues such as biases, leading to unreliable outcomes and misplaced confidence. While model explanation techniques, particularly visual explanations, offer valuable insights by elucidating model attributions of their decision, many limitations still exist -- They are primarily instance-based and not scalable across the dataset, and they provide one-directional information from the model to the human side, lacking a mechanism for users to address detected issues. To fulfill these gaps, we introduce HILAD, a novel framework designed to foster a dynamic and bidirectional collaboration between humans and AI for enhancing anomaly detection models in time series. Through our visual interface, HILAD empowers domain experts to detect, interpret, and correct unexpected model behaviors at scale. Our evaluation through user studies with two models and three time series datasets demonstrates the effectiveness of HILAD, which fosters a deeper model understanding, immediate corrective actions, and model reliability enhancement.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 42 of its 77 references that are in the map. First posted on arXiv 6 May 2024.

Builds on

42 of 77 references.

References · 42

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  6. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  8. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  9. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  10. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 582
  11. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 453
  12. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
30 more
  1. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 360
  2. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 214
  3. 2019MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscited by 176
  4. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 151
  5. 2021Voice2Series: Reprogramming Acoustic Models for Time Series Classificationcited by 91
  6. 2015Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmarkcited by 88
  7. 2021Gated Transformer Networks for Multivariate Time Series Classificationcited by 58
  8. 2020TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networkscited by 55
  9. 2024Multimodal Healthcare AI: Identifying and Designing Clinically Relevant Vision-Language Applications for Radiologycited by 45
  10. 2020VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detectioncited by 28
  11. 2022Unsupervised Model Selection for Time-series Anomaly Detectioncited by 25
  12. 2020Why model why? Assessing the strengths and limitations of LIMEcited by 21
  13. 2022Constructing Large-Scale Real-World Benchmark Datasets for AIOpscited by 20
  14. 2022A Unified Understanding of Deep NLP Models for Text Classificationcited by 18
  15. 2022Sintel: A Machine Learning Framework to Extract Insights from Signalscited by 16
  16. 2022Core Risk Minimization using Salient ImageNetcited by 15
  17. 2020Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Seriescited by 13
  18. 2022Diagnosing Ensemble Few-Shot Classifierscited by 13
  19. 2020XNAP: Making LSTM-based Next Activity Predictions Explainable by Using LRPcited by 12
  20. 2021VAC-CNN: A Visual Analytics System for Comparative Studies of Deep Convolutional Neural Networkscited by 11
  21. 2021MTV: Visual Analytics for Detecting, Investigating, and Annotating Anomalies in Multivariate Time Seriescited by 11
  22. 2020A Visual Analytics Framework for Reviewing Multivariate Time-Series Data with Dimensionality Reductioncited by 9
  23. 2022MTSMAE: Masked Autoencoders for Multivariate Time-Series Forecastingcited by 9
  24. 2019SAX Navigator: Time Series Exploration through Hierarchical Clusteringcited by 7
  25. 2023LabelVizier: Interactive Validation and Relabeling for Technical Text Annotationscited by 7
  26. 2023Interactive Reweighting for Mitigating Label Quality Issuescited by 7
  27. 2024AttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Findingcited by 6
  28. 2023SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspectivecited by 5
  29. 2021Time Series Anomaly Detection with label-free Model Selectioncited by 3
  30. 2023TimePool: Visually Answer "Which and When" Questions On Univariate Time Seriescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentationcited by 9
  2. 2026Self-Adaptive Anomaly Detection with Reinforcement Learning and Human Feedback in Connected Vehiclescited by 0
  3. 2026Training-Free Human-in-the-Loop Anomaly Detection via Memory Bank Correctioncited by 0