Universal anomaly detection still remains a challenging prob- lem in machine learning and medical image analysis. It is possible to learn an expected distribution from a single class of normative samples, e.g., through epistemic uncertainty estimates, auto-encoding models, or from synthetic anomalies in a self-supervised way. The performance of self-supervised anomaly detection approaches is still inferior compared to methods that use examples from known unknown classes to shape the decision boundary. However, outlier exposure methods often do not identify unknown unknowns. Here we discuss an improved self-supervised single-class training strategy that supports the approximation of proba- bilistic inference with loosen feature locality constraints. We show that up-scaling of gradients with histogram-equalised images is beneficial for recently proposed self-supervision tasks. Our method is integrated into several out-of-distribution (OOD) detection models and we show evi- dence that our method outperforms the state-of-the-art on various bench- mark datasets. Source code will be publicly available by the time of the conference.

翻译：通用异常检测在机器学习与医学影像分析中仍是一项具有挑战性的问题。通过单类规范性样本学习预期分布是可行的，例如利用认知不确定性估计、自编码模型或自监督方式生成的合成异常。自监督异常检测方法的性能仍逊于那些利用已知未知类别的示例来塑造决策边界的方法。然而，异常暴露方法通常无法识别未知的未知。本文讨论了一种改进的自监督单类训练策略，该策略通过放宽特征局部性约束来支持概率推断的近似。研究表明，对直方图均衡化图像进行梯度放大有助于提升近期提出的自监督任务性能。我们将所提方法集成到多种分布外（OOD）检测模型中，并证明该方法在多个基准数据集上优于现有最优技术。源代码将于会议期间公开提供。