Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly Detection

Abstract

Video anomaly detection under weak labels is formulated as a typical multiple-instance learning problem in previous works. In this paper, we provide a new perspective, i.e., a supervised learning task under noisy labels. In such a viewpoint, as long as cleaning away label noise, we can directly apply fully supervised action classifiers to weakly supervised anomaly detection, and take maximum advantage of these well-developed classifiers. For this purpose, we devise a graph convolutional network to correct noisy labels. Based upon feature similarity and temporal consistency, our network propagates supervisory signals from high-confidence snippets to low-confidence ones. In this manner, the network is capable of providing cleaned supervision for action classifiers. During the test phase, we only need to obtain snippet-wise predictions from the action classifier without any extra post-processing. Extensive experiments on 3 datasets at different scales with 2 types of action classifiers demonstrate the efficacy of our method. Remarkably, we obtain the frame-level AUC score of 82.12% on UCF-Crime.

Anomaly Event Detection in Security Surveillance Using Two-Stream Based Model

“…is dataset cannot be utilized directly to perform anomaly event detection because the training set has no abnormal video. To tackle this problem, Zhong et al [48] rebuilt the dataset via randomly choosing abnormal test videos and putting them into the training data and vice versa. Simultaneously, both training and test dataset contain 13 scenes.…”

“…is new organization of dataset made it suitable for anomaly event detection task. us, we perform the same operation as that in [48], before executing the experiments.…”

“…ey are receiver operating characteristic (ROC) curve and the area under the curve (AUC), respectively. e reason we utilize ROC and AUC is that they are two popular metrics for anomaly event detection tasks [13,21,48]. For fair comparison with other works and to verify the effectiveness of our model, ROC and AUC are employed.…”

Global Information Guided Video Anomaly Detection

“…In this section, we briefly review the techniques of video anomaly detection under weak supervision. Recently there are researches employing normal and abnormal video data along with video-level annotations, for model building [4,8,11,12]. Among them, Multiple Instance Learning (MIL) is introduced for pattern modeling [4,8,12].…”

“…After mining the global information, we further analyze the relationship between each spatio-temporal vector and the GPC vector to retrieve spatial cue vital for anomaly classification and localization. Previous methods [8,11,12] usually apply a global_pooling operation to integrate the spatial information, however in this way, the object appearance cues and the interaction between objects are largely neglected, which is of great importance for distinguishing the anomalies. For example, the instances of Robbery, Stealinд and Shootinд are prone to false detection.…”