CKNN：用于无监督视频异常检测的清洗k近邻方法
CKNN: Cleansed k-Nearest Neighbor for Unsupervised Video Anomaly Detection
AI总结：
本文针对无监督视频异常检测中训练数据含异常导致“异常聚类”的问题，提出清洗k近邻方法CKNN，通过清洗训练集过滤异常聚类，在多个基准上AUROC最高提升8.5%，性能媲美使用无异常数据训练的最先进方法。
摘要：
在本文中，我们研究无监督视频异常检测（UVAD）问题。该任务旨在使用未标注视频作为训练数据来检测测试视频中的异常事件。训练数据中异常的存在对该任务构成重大挑战，尤其是因为它们在特征空间中形成聚类。我们将这一特性称为“异常聚类”问题。这些异常的凝聚特性使得在训练集中区分正常数据和异常数据变得困难。因此，使用未标注数据集训练传统异常检测技术往往会导致次优结果。为应对这一困难，我们提出了一种名为Cleansed k-Nearest Neighbor（CKNN）的新方法，该方法通过清洗训练数据集来显式过滤掉异常聚类。在特征空间中遵循k近邻算法可提供强大的异常检测能力。尽管所识别的异常聚类问题对在UVAD中应用k近邻构成了重大挑战，但我们提出的清洗方案有效地解决了这一问题。我们在多个基准数据集上评估了所提出的方法，并证明CKNN在AUROC指标上比先前最先进的UVAD方法高出最多8.5%（从82.0提升至89.0）。此外，我们强调所提出方法的性能与使用无异常数据训练的最先进方法相当。
英文摘要：
In this paper, we address the problem of unsupervised video anomaly detection (UVAD). The task aims to detect abnormal events in test video using unlabeled videos as training data. The presence of anomalies in the training data poses a significant challenge in this task, particularly because they form clusters in the feature space. We refer to this property as the "Anomaly Cluster" issue. The condensed nature of these anomalies makes it difficult to distinguish between normal and abnormal data in the training set. Consequently, training conventional anomaly detection techniques using an unlabeled dataset often leads to sub-optimal results. To tackle this difficulty, we propose a new method called Cleansed k-Nearest Neighbor (CKNN), which explicitly filters out the Anomaly Clusters by cleansing the training dataset. Following the k-nearest neighbor algorithm in the feature space provides powerful anomaly detection capability. Although the identified Anomaly Cluster issue presents a significant challenge to applying k-nearest neighbor in UVAD, our proposed cleansing scheme effectively addresses this problem. We evaluate the proposed method on various benchmark datasets and demonstrate that CKNN outperforms the previous state-of-the-art UVAD method by up to 8.5% (from 82.0 to 89.0) in terms of AUROC. Moreover, we emphasize that the performance of the proposed method is comparable to that of the state-of-the-art method trained using anomaly-free data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
