Deep anomaly detection (AD) aims to provide robust and efficient classifiers for one-class and unbalanced settings. However current AD models still struggle on edge-case normal samples and are often unable to keep high performance over different scales of anomalies. Moreover, there currently does not exist a unified framework efficiently covering both one-class and unbalanced learnings. In the light of these limitations, we introduce a new two-stage anomaly detector which memorizes during training multi-scale normal prototypes to compute an anomaly deviation score. First, we simultaneously learn representations and memory modules on multiple scales using a novel memory-augmented contrastive learning. Then, we train an anomaly distance detector on the spatial deviation maps between prototypes and observations. Our model highly improves the state-of-the-art performance on a wide range of object, style and local anomalies with up to 50% error relative improvement on CIFAR-100. It is also the first model to keep high performance across the one-class and unbalanced settings.

翻译：深度异常检测（AD）旨在为一类分类和不平衡场景提供鲁棒且高效的分类器。然而，当前AD模型在处理边缘案例的正常样本时仍面临挑战，且通常无法在不同尺度的异常上保持高性能。此外，目前尚无统一框架能够高效覆盖一类分类与不平衡学习。针对这些局限，我们提出一种新型两阶段异常检测器，通过记忆训练过程中多尺度的正常原型来计算异常偏差分数。首先，我们采用新型记忆增强对比学习，同时在多个尺度上学习表示与记忆模块；其次，基于原型与观测值之间的空间偏差图训练异常距离检测器。该模型在目标、风格及局部异常等广泛场景中显著提升了现有技术水平，在CIFAR-100上实现最高50%的相对错误率降低。它也是首个在一类分类与不平衡场景下均保持高性能的模型。