Surrogate task based methods have recently shown great promise for unsupervised image anomaly detection. However, there is no guarantee that the surrogate tasks share the consistent optimization direction with anomaly detection. In this paper, we return to a direct objective function for anomaly detection with information theory, which maximizes the distance between normal and anomalous data in terms of the joint distribution of images and their representation. Unfortunately, this objective function is not directly optimizable under the unsupervised setting where no anomalous data is provided during training. Through mathematical analysis of the above objective function, we manage to decompose it into four components. In order to optimize in an unsupervised fashion, we show that, under the assumption that distribution of the normal and anomalous data are separable in the latent space, its lower bound can be considered as a function which weights the trade-off between mutual information and entropy. This objective function is able to explain why the surrogate task based methods are effective for anomaly detection and further point out the potential direction of improvement. Based on this object function we introduce a novel information theoretic framework for unsupervised image anomaly detection. Extensive experiments have demonstrated that the proposed framework significantly outperforms several state-of-the-arts on multiple benchmark data sets.
翻译:以替代任务为基础的方法最近显示出了不受监督的图像异常现象探测的巨大前景。 但是, 代理任务无法保证与异常现象探测具有一致的优化方向。 在本文中, 我们返回到一个直接客观的功能, 用信息理论探测异常现象, 使正常和异常数据在图像联合分布及其表达方式上的距离最大化。 不幸的是, 在未经监督的环境下, 没有在培训期间提供异常数据, 这个目标功能无法直接优化。 通过对上述目标功能进行数学分析, 我们设法将它分解为四个组成部分。 为了在不受监督的情况下优化它。 在假设正常和异常数据在潜在空间的分布是可相互比较的的情况下, 其较低界限可以被视为一个函数, 将相互信息与酶之间的交易加权。 这个目标功能能够解释为什么以替代任务为基础的方法对异常现象检测有效, 并进一步指出可能的改进方向。 基于此对象的功能, 为了在不受监督的情况下优化它的方式优化。 我们展示了一个新的信息、 和异常数据数据分布在潜在空间中, 其较低的边框可以被视为一个函数, 大大超越了多个图像检测基准状态。