RangeAD: Fast On-Model Anomaly Detection
AI 摘要
RangeAD通过利用主模型的神经元输出范围进行异常检测,实现了高性能和低推理成本。
主要贡献
- 提出了On-Model AD的概念,利用现有模型进行异常检测
- 提出了RangeAD算法,使用神经元输出范围进行异常检测
- 实验证明RangeAD在高维任务上表现优异且推理成本低
方法论
RangeAD算法利用主模型中神经元的输出范围作为异常检测的依据,无需额外的独立AD模型。
原文摘要
In practice, machine learning methods commonly require anomaly detection (AD) to filter inputs or detect distributional shifts. Typically, this is implemented by running a separate AD model alongside the primary model. However, this separation ignores the fact that the primary model already encodes substantial information about the target distribution. In this paper, we introduce On-Model AD, a setting for anomaly detection that explicitly leverages access to a related machine learning model. Within this setting, we propose RangeAD, an algorithm that utilizes neuron-wise output ranges derived from the primary model. RangeAD achieves superior performance even on high-dimensional tasks while incurring substantially lower inference costs. Our results demonstrate the potential of the On-Model AD setting as a practical framework for efficient anomaly detection.