Fine-grained anomaly detection has recently been dominated by segmentation based approaches. These approaches first classify each element of the sample (e.g., image patch) as normal or anomalous and then classify the entire sample as anomalous if it contains anomalous elements. However, such approaches do not extend to scenarios where the anomalies are expressed by an unusual combination of normal elements. In this paper, we overcome this limitation by proposing set features that model each sample by the distribution its elements. We compute the anomaly score of each sample using a simple density estimation method. Our simple-to-implement approach outperforms the state-of-the-art in image-level logical anomaly detection (+3.4%) and sequence-level time-series anomaly detection (+2.4%).
翻译:精细的异常现象检测最近以分解法为主。 这些方法首先将样本的每个元素(如图像补丁)分类为正常或异常,然后将整个样本如果含有异常元素,则归类为异常元素。 但是,这些方法并不延伸至异常现象表现为正常元素不同寻常组合的情景。 在本文中, 我们通过提出每个样本的设定特征, 以其分布元素为模型, 克服了这一限制。 我们使用简单的密度估计方法计算了每个样本的异常分数。 我们的简单到执行方法超过了图像层面逻辑异常检测(+3.4%)和序列时间序列异常检测(+2.4%)方面的最新水平。