Anomaly detection is widely used in network intrusion detection, autonomous driving, medical diagnosis, credit card frauds, etc. However, several key challenges remain open, such as lack of ground truth labels, presence of complex temporal patterns, and generalizing over different datasets. This paper proposes TSI-GAN, an unsupervised anomaly detection model for time-series that can learn complex temporal patterns automatically and generalize well, i.e., no need for choosing dataset-specific parameters, making statistical assumptions about underlying data, or changing model architectures. To achieve these goals, we convert each input time-series into a sequence of 2D images using two encoding techniques with the intent of capturing temporal patterns and various types of deviance. Moreover, we design a reconstructive GAN that uses convolutional layers in an encoder-decoder network and employs cycle-consistency loss during training to ensure that inverse mappings are accurate as well. In addition, we also instrument a Hodrick-Prescott filter in post-processing to mitigate false positives. We evaluate TSI-GAN using 250 well-curated and harder-than-usual datasets and compare with 8 state-of-the-art baseline methods. The results demonstrate the superiority of TSI-GAN to all the baselines, offering an overall performance improvement of 13% and 31% over the second-best performer MERLIN and the third-best performer LSTM-AE, respectively.

翻译：异常检测广泛应用于网络入侵检测、自动驾驶、医学诊断和信用卡欺诈等领域。然而，仍存在若干关键挑战，例如缺乏真实标签、复杂时间模式的存在以及在不同数据集上的泛化问题。本文提出TSI-GAN，一种无监督时间序列异常检测模型，能够自动学习复杂的时间模式并具有良好的泛化能力，即无需选择数据集特定参数、对底层数据做出统计假设或更改模型架构。为实现这些目标，我们采用两种编码技术将每个输入时间序列转换为一组二维图像序列，旨在捕捉时间模式和各种偏差类型。此外，我们设计了一种基于生成对抗网络的重构模型，在编码器-解码器网络中使用卷积层，并在训练过程中采用循环一致性损失以确保逆映射的准确性。同时，我们在后处理中引入霍德里克-普雷斯科特滤波器以减少误报。我们使用250个精心筛选且难度高于常规的数据集评估TSI-GAN，并与8种最先进基线方法进行比较。结果表明TSI-GAN优于所有基线方法，整体性能较第二名MERLIN和第三名LSTM-AE分别提升13%和31%。