通过后处理校准提升无监督异常检测的准确性与定位能力
Post-Hoc Calibrated Anomaly Detection
- 使用后处理校准（Platt缩放、Beta校准）优化模型输出置信度
- 在梯度扰动和随机合成频谱数据上校准效果更优，提升检测精度
- 适合需要高置信度异常定位的工业质检、医学影像等场景
深度无监督异常检测在引入外部异常数据进行离群点暴露训练后取得了进展，这为探索后处理校准在异常检测与定位中的有效性提供了可能。研究发现，后处理Platt缩放和Beta校准能有效提升基于梯度输入扰动的方法性能；同时，在仅使用基础模型的无监督损失预训练后，采用严格恰当损失进行后处理训练也表现良好。此外，实验表明以随机合成的频谱数据作为标注异常样本进行校准，有时比传统离群点暴露更具优势，暗示离群点暴露主要适用于初始训练阶段。
原文摘要 · Abstract (English)
Deep unsupervised anomaly detection has seen improvements in a supervised binary classification paradigm in which auxiliary external data is included in the training set as anomalous data in a process referred to as outlier exposure, which opens the possibility of exploring the efficacy of post-hoc calibration for anomaly detection and localization. Post-hoc Platt scaling and Beta calibration are found to improve results with gradient-based input perturbation, as well as post-hoc training with a strictly proper loss of a base model initially trained on an unsupervised loss. Post-hoc calibration is also found at times to be more effective using random synthesized spectral data as labeled anomalous data in the calibration set, suggesting that outlier exposure is superior only for initial training.
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。