用扩散模型生成异常修复的反事实解释，让异常原因一目了然。
AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
- 基于扩散模型生成非异常版本的反事实样本，直观展示修复方向。
- 在多个视觉与时序异常数据集上验证有效，提升解释可读性。
- 无需领域知识，统一框架支持生成与评估解释，适合工业部署。
异常检测广泛用于识别关键错误和可疑行为，但现有方法缺乏可解释性。我们结合现有方法的共性与生成模型的最新进展，提出针对异常检测的反事实解释。给定输入，通过基于扩散的修复生成其反事实样本，展现非异常状态应呈现的样子。该方法的关键优势在于实现领域无关的形式化解释标准，构建统一的解释生成与评估框架。我们在视觉（MVTec、VisA）和时序（SWaT、WADI、HAI）异常数据集上验证了该框架的有效性。实验代码已公开于：https://github.com/xjiae/arpro。
原文摘要 · Abstract (English)
Anomaly detection is widely used for identifying critical errors and suspicious behaviors, but current methods lack interpretability. We leverage common properties of existing methods and recent advances in generative models to introduce counterfactual explanations for anomaly detection. Given an input, we generate its counterfactual as a diffusion-based repair that shows what a non-anomalous version should have looked like. A key advantage of this approach is that it enables a domain-independent formal specification of explainability desiderata, offering a unified framework for generating and evaluating explanations. We demonstrate the effectiveness of our anomaly explainability framework, AR-Pro, on vision (MVTec, VisA) and time-series (SWaT, WADI, HAI) anomaly datasets. The code used for the experiments is accessible at: https://github.com/xjiae/arpro.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。