论文标题
域适应性检测异常
Anomaly Detection with Domain Adaptation
论文作者
论文摘要
我们研究了针对域适应的半监督异常检测的问题。鉴于来自源域的一组正常数据和目标域的有限量示例，目标是在目标域中具有表现良好的异常检测器。我们提出不变表示异常检测（IRAD）来解决这个问题，在此我们首先学会提取域不变表示。提取是通过通过对抗性学习和特定于源的编码器和发电机一起训练的跨域编码器来实现的。然后使用学习的表示训练异常检测器。我们在数字图像数据集（MNIST，USPS和SVHN）和对象识别数据集（Office-home）上广泛评估IRAD。实验结果表明，IRAD在不同数据集上超过基线模型。我们为关节误差提供了一个理论下限，该结合解释了过度训练的性能衰减，也解释了概括误差的上限。
We study the problem of semi-supervised anomaly detection with domain adaptation. Given a set of normal data from a source domain and a limited amount of normal examples from a target domain, the goal is to have a well-performing anomaly detector in the target domain. We propose the Invariant Representation Anomaly Detection (IRAD) to solve this problem where we first learn to extract a domain-invariant representation. The extraction is achieved by an across-domain encoder trained together with source-specific encoders and generators by adversarial learning. An anomaly detector is then trained using the learnt representations. We evaluate IRAD extensively on digits images datasets (MNIST, USPS and SVHN) and object recognition datasets (Office-Home). Experimental results show that IRAD outperforms baseline models by a wide margin across different datasets. We derive a theoretical lower bound for the joint error that explains the performance decay from overtraining and also an upper bound for the generalization error.
