DQE: A Semantic-Aware Evaluation Metric for Time Series Anomaly Detection

• URL: http://arxiv.org/abs/2603.06131v1
• Date: Fri, 06 Mar 2026 10:38:51 GMT
• Title: DQE: A Semantic-Aware Evaluation Metric for Time Series Anomaly Detection
• Abstract summary: We revisit the evaluation of time series anomaly detection from the perspective of detection semantics.<n>We introduce a partitioning strategy grounded in detection semantics, which decomposes the local temporal region of each anomaly into three functionally distinct subregions.<n>Using this partitioning, we evaluate overall detection behavior across events and design finer-grained scoring mechanisms for each subregion, enabling more reliable and interpretable assessment.
• Score: 10.700735533120257
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time series anomaly detection has achieved remarkable progress in recent years. However, evaluation practices have received comparatively less attention, despite their critical importance. Existing metrics exhibit several limitations: (1) bias toward point-level coverage, (2) insensitivity or inconsistency in near-miss detections, (3) inadequate penalization of false alarms, and (4) inconsistency caused by threshold or threshold-interval selection. These limitations can produce unreliable or counterintuitive results, hindering objective progress. In this work, we revisit the evaluation of time series anomaly detection from the perspective of detection semantics and propose a novel metric for more comprehensive assessment. We first introduce a partitioning strategy grounded in detection semantics, which decomposes the local temporal region of each anomaly into three functionally distinct subregions. Using this partitioning, we evaluate overall detection behavior across events and design finer-grained scoring mechanisms for each subregion, enabling more reliable and interpretable assessment. Through a systematic study of existing metrics, we identify an evaluation bias associated with threshold-interval selection and adopt an approach that aggregates detection qualities across the full threshold spectrum, thereby eliminating evaluation inconsistency. Extensive experiments on synthetic and real-world data demonstrate that our metric provides stable, discriminative, and interpretable evaluation, while achieving robust assessment compared with ten widely used metrics.

Related papers

• Beyond Nodes vs. Edges: A Multi-View Fusion Framework for Provenance-Based Intrusion Detection [6.343815622517112]
  PROVfusion is a multi-view anomaly fusion framework for provenance-based intrusion detection.<n>It fuses heterogeneous anomaly signals through lightweight fusion schemes and determines the final anomaly decisions through a voting-based integration process.<n>Experiments on nine widely used benchmark entity datasets demonstrate that PROVfusion achieves higher detection accuracy and lower false-positive rates than single node- and edge-centric baselines.
  arXiv  Detail & Related papers  (2026-04-16T06:40:50Z)
• A Problem-Oriented Taxonomy of Evaluation Metrics for Time Series Anomaly Detection [11.114573387946498]
  Time series anomaly detection is widely used in IoT and cyber-physical systems.<n>This study introduces a problem-oriented framework that reinterprets existing metrics based on the specific evaluation challenges they are designed to address.
  arXiv  Detail & Related papers  (2025-11-24T04:09:04Z)
• Rethinking Metrics and Benchmarks of Video Anomaly Detection [58.37571339811799]
  Video Anomaly Detection (VAD) aims to detect anomalies that deviate from expectation.<n>Existing VAD metrics are influenced by single annotation bias.<n>Existing benchmarks lack the capability to evaluate scene overfitting of fully/weakly-supervised algorithms.
  arXiv  Detail & Related papers  (2025-05-25T08:09:42Z)
• OIPR: Evaluation for Time-series Anomaly Detection Inspired by Operator Interest [26.460594836601004]
  We propose a novel set of time-series anomaly detection evaluation metrics, called OIPR.<n>OIPR models the process of operators receiving detector alarms and handling faults, utilizing area under the operator interest curve to evaluate the performance of TAD algorithms.<n>It achieves a balance between point and event perspectives, overcoming their primary limitations and offering applicability to broader situations.
  arXiv  Detail & Related papers  (2025-03-03T07:37:24Z)
• A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection [89.92916473403108]
  This paper proposes a comprehensive visual anomaly detection benchmark, ADer, which is a modular framework for new methods.<n>The benchmark includes multiple datasets from industrial and medical domains, implementing fifteen state-of-the-art methods and nine comprehensive metrics.<n>We objectively reveal the strengths and weaknesses of different methods and provide insights into the challenges and future directions of multi-class visual anomaly detection.
  arXiv  Detail & Related papers  (2024-06-05T13:40:07Z)
• On Pixel-level Performance Assessment in Anomaly Detection [87.7131059062292]
  Anomaly detection methods have demonstrated remarkable success across various applications. However, assessing their performance, particularly at the pixel-level, presents a complex challenge. In this paper, we dissect the intricacies of this challenge, underscored by visual evidence and statistical analysis.
  arXiv  Detail & Related papers  (2023-10-25T08:02:27Z)
• DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection [55.70982767084996]
  A critical yet frequently overlooked challenge in the field of deepfake detection is the lack of a standardized, unified, comprehensive benchmark. We present the first comprehensive benchmark for deepfake detection, called DeepfakeBench, which offers three key contributions. DeepfakeBench contains 15 state-of-the-art detection methods, 9CL datasets, a series of deepfake detection evaluation protocols and analysis tools, as well as comprehensive evaluations.
  arXiv  Detail & Related papers  (2023-07-04T01:34:41Z)
• SoftED: Metrics for Soft Evaluation of Time Series Event Detection [4.139895427110409]
  Time series event detection methods are evaluated mainly by standard classification metrics that focus solely on detection accuracy.<n>Inaccuracy in detecting an event can often result from its preceding or delayed effects reflected in neighboring detections.<n>This paper introduces SoftED metrics, a new set of metrics designed for soft evaluating event detection methods.
  arXiv  Detail & Related papers  (2023-04-02T03:27:31Z)
• PULL: Reactive Log Anomaly Detection Based On Iterative PU Learning [58.85063149619348]
  We propose PULL, an iterative log analysis method for reactive anomaly detection based on estimated failure time windows. Our evaluation shows that PULL consistently outperforms ten benchmark baselines across three different datasets.
  arXiv  Detail & Related papers  (2023-01-25T16:34:43Z)
• Unsupervised Anomaly Detection in Time-series: An Extensive Evaluation and Analysis of State-of-the-art Methods [10.618572317896515]
  Unsupervised anomaly detection in time-series has been extensively investigated in the literature. This paper proposes an in-depth evaluation study of recent unsupervised anomaly detection techniques in time-series.
  arXiv  Detail & Related papers  (2022-12-06T15:05:54Z)
• Uncertainty-aware Score Distribution Learning for Action Quality Assessment [91.05846506274881]
  We propose an uncertainty-aware score distribution learning (USDL) approach for action quality assessment (AQA) Specifically, we regard an action as an instance associated with a score distribution, which describes the probability of different evaluated scores. Under the circumstance where fine-grained score labels are available, we devise a multi-path uncertainty-aware score distributions learning (MUSDL) method to explore the disentangled components of a score.
  arXiv  Detail & Related papers  (2020-06-13T15:41:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.