CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection

2020/11/24 by Muhammad Zaigham Zaheer, Arif Mahmood, Zaheer, Muhammad Zaigham +5 · 7 citations
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Artificial Immune Systems Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Network Security and Intrusion Detection

paper · pdf · doi:10.48550/arxiv.2011.12077

openalex publication_date 2020/11/24 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

Learning to detect real-world anomalous events through video-level labels is a challenging task due to the rare occurrence of anomalies as well as noise in the labels. In this work, we propose a weakly supervised anomaly detection method which has manifold contributions including1) a random batch based training procedure to reduce inter-batch correlation, 2) a normalcy suppression mechanism to minimize anomaly scores of the normal regions of a video by taking into account the overall information available in one training batch, and 3) a clustering distance based loss to contribute towards mitigating the label noise and to produce better anomaly representations by encouraging our model to generate distinct normal and anomalous clusters. The proposed method obtains83.03% and 89.67% frame-level AUC performance on the UCF Crime and ShanghaiTech datasets respectively, demonstrating its superiority over the existing state-of-the-art algorithms.

Cited by

• Recognition of Abnormal Events in Surveillance Videos using Weakly Supervised Dual-Encoder Models
• RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection
• RobustA: Robust Anomaly Detection in Multimodal Data
• Knowledge-Guided Textual Reasoning for Explainable Video Anomaly Detection via LLMs
• Aligning Effective Tokens with Video Anomaly in Large Language Models
• The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM
• DAMS:Dual-Branch Adaptive Multiscale Spatiotemporal Framework for Video Anomaly Detection

Related

• Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos
• Weakly Supervised Video Anomaly Detection Based on Cross-Batch Clustering Guidance
• A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selection
• Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection
• Real-world Anomaly Detection in Surveillance Videos