Few-shot Anomaly Detection and Classification Through Reinforced Data Selection
Few-shot Anomaly Detection and Classification Through Reinforced Data Selection
复制标题
DOI：
10.1109/icdm54844.2022.00115
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Xiao Han;Depeng Xu;Shuhan Yuan;Xintao Wu
中科院分区：
文献类型：
--
作者：
Xiao Han;Depeng Xu;Shuhan Yuan;Xintao Wu
由于异常的稀缺性，深度异常检测模型主要以无监督或半监督的方式训练，这取决于少量标记样本的可用性。目前，大多数非监督方法通过识别偏离模式来检测异常，一些半监督研究也使用标记异常来提高性能。然而，很少有研究集中于如何利用容易获得的大规模未标记数据集中的潜在异常。同时，在半监督环境下，虽然我们假设有少量的标记异常，但异常分类的任务没有得到充分利用。本文针对给定有限的已标记样本和大量未标记样本的异常检测与分类问题，提出了一种基于强化数据选择的少射异常检测与分类模型(FADS)，该框架通过探索未标记数据集来扩充训练集，从而迭代地提高异常检测与分类的性能。实验结果表明，FADS算法在初始标记样本较少的情况下，能够提高异常检测和分类的性能。
Due to the scarcity of anomalies, deep anomaly detection models are predominately trained in an unsupervised or semi-supervised manner depending on the availability of a small number of labeled samples. Currently, most unsupervised approaches detect anomalies by identifying the deviate patterns, and some semi-supervised studies also use labeled anomalies to improve performance. However, few studies have focused on how to take advantage of potential anomalies in an easily obtained and large-scale unlabeled dataset. Meanwhile, in a semi-supervised setting, although we assume having a small number of labeled anomalies, the task of anomaly classification is under-exploited. In this work, considering the problem of anomaly detection and classification by giving limited labeled samples as well as a large number of unlabeled samples, we propose a few-shot anomaly detection and classification model through reinforced data selection (FADS), a novel framework that iteratively improves the performance of anomaly detection and classification by exploring the unlabeled dataset to augment the training set. Experimental results show that FADS is able to improve the performance of anomaly detection and classification with only a few labeled samples initially.