CL-Flow：通过对比学习强化归一化流以实现更优的异常检测
CL-Flow:Strengthening the Normalizing Flows by Contrastive Learning for Better Anomaly Detection
AI总结：
提出CL-Flow，结合对比学习与2D-Flow的自监督异常检测方法，通过合成异常样本和代理任务微调网络，实现高精度、轻量且快速的端到端检测，在MVTecAD和BTAD上分别达到99.6%和96.8%的AUROC。
摘要：
在异常检测领域，异常样本的稀缺性使得当前研究重点转向无监督异常检测。尽管这些无监督异常检测方法提供了便利，但它们也忽略了嵌入在异常样本中的关键先验信息。此外，在众多深度学习方法中，监督方法通常表现出优于无监督方法的性能。考虑到上述原因，我们提出了一种自监督异常检测方法，该方法将对比学习与2D-Flow相结合，以实现更精确的检测结果和更快的推理过程。一方面，我们引入了一种新的异常合成方法，根据真实的工业场景生成异常样本及其代理标注。另一方面，在获得大量异常样本后，我们通过引入对比学习来增强2D-Flow框架，利用多样化的代理任务对网络进行微调。我们的方法使网络能够从自生成标签中学习更精确的映射关系，同时保留2D-Flow的轻量特性。与主流的无监督方法相比，我们的自监督方法展现出更高的检测精度、更少的额外模型参数和更快的推理速度。此外，整个训练和推理过程是端到端的。我们的方法展示了新的最先进结果，在MVTecAD数据集上实现了99.6%的图像级AUROC，在BTAD数据集上实现了96.8%的图像级AUROC。
英文摘要：
In the anomaly detection field, the scarcity of anomalous samples has directed the current research emphasis towards unsupervised anomaly detection. While these unsupervised anomaly detection methods offer convenience, they also overlook the crucial prior information embedded within anomalous samples. Moreover, among numerous deep learning methods, supervised methods generally exhibit superior performance compared to unsupervised methods. Considering the reasons mentioned above, we propose a self-supervised anomaly detection approach that combines contrastive learning with 2D-Flow to achieve more precise detection outcomes and expedited inference processes. On one hand, we introduce a novel approach to anomaly synthesis, yielding anomalous samples in accordance with authentic industrial scenarios, alongside their surrogate annotations. On the other hand, having obtained a substantial number of anomalous samples, we enhance the 2D-Flow framework by incorporating contrastive learning, leveraging diverse proxy tasks to fine-tune the network. Our approach enables the network to learn more precise mapping relationships from self-generated labels while retaining the lightweight characteristics of the 2D-Flow. Compared to mainstream unsupervised approaches, our self-supervised method demonstrates superior detection accuracy, fewer additional model parameters, and faster inference speed. Furthermore, the entire training and inference process is end-to-end. Our approach showcases new state-of-the-art results, achieving a performance of 99.6\% in image-level AUROC on the MVTecAD dataset and 96.8\% in image-level AUROC on the BTAD dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
