Dynamic Distinction Learning: Adaptive Pseudo Anomalies for Video Anomaly Detection

2024/04/07 by Demetris Lappas, Lappas, Demetris, Vasileios Argyriou +3 · 1 citation
Computer Science · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Network Security and Intrusion Detection

paper · doi:10.48550/arxiv.2404.04986

openalex publication_date 2024/04/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

We introduce Dynamic Distinction Learning (DDL) for Video Anomaly Detection, a novel video anomaly detection methodology that combines pseudo-anomalies, dynamic anomaly weighting, and a distinction loss function to improve detection accuracy. By training on pseudo-anomalies, our approach adapts to the variability of normal and anomalous behaviors without fixed anomaly thresholds. Our model showcases superior performance on the Ped2, Avenue and ShanghaiTech datasets, where individual models are tailored for each scene. These achievements highlight DDL's effectiveness in advancing anomaly detection, offering a scalable and adaptable solution for video surveillance challenges.

Cited by

• ALFred: An Active Learning Framework for Real-world Semi-supervised Anomaly Detection with Adaptive Thresholds

Related

• A Discriminative Framework for Anomaly Detection in Large Videos
• Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learning
• PA-VAD: Diffusion-Based Pseudo-Only Video Anomaly Detection via Domain-Aligned Memory Updates
• Real-world Video Anomaly Detection by Extracting Salient Features in Videos
• Real-world Anomaly Detection in Surveillance Videos